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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash

    This neuron detects programming/code segments (e.g. Python code blocks and their tokens) rather than normal prose.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    anticipated
    -0.06
    runs
    -0.06
     desired
    -0.06
     tren
    -0.06
    凌
    -0.06
    指
    -0.06
    яс
    -0.06
    visited
    -0.06
    eleri
    -0.06
    êu
    -0.06
    POSITIVE LOGITS
    ầm
    0.07
    แห
    0.07
    {},
    0.07
     села
    0.06
     بج
    0.06
    329
    0.06
    spr
    0.06
    (targetEntity
    0.06
    achinery
    0.06
    (PDO
    0.06
    Act Density 0.031%

    No Known Activations