Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is pick out tokens that are being used as labels or identifiers—names of menu items, translation‐strings, types, functions, variables, list entries, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    elements related to programming and scripting tasks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Url
    -0.07
     snacks
    -0.06
     bacterial
    -0.06
    (symbol
    -0.06
     değiş
    -0.06
     NumberOf
    -0.06
    _QUESTION
    -0.06
     نظری
    -0.06
     xf
    -0.06
    άλυψης
    -0.06
    POSITIVE LOGITS
     diseñ
    0.06
    放送
    0.06
     Fres
    0.06
    .at
    0.06
     نور
    0.06
    }));↵
    0.06
     hộ
    0.06
     Paran
    0.06
     encountering
    0.06
     onemoc
    0.06
    Act Density 0.101%

    No Known Activations