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

    Neuronpedia

    INDEX
    Explanations

    scientific text

    np_max-act · gemini-2.0-flash

    The neuron activates on capitalized named entities (proper nouns) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    [level
    -0.07
    Parameters
    -0.06
     Watson
    -0.06
     Adoption
    -0.06
    membership
    -0.06
    amac
    -0.06
     человеч
    -0.06
     حافظ
    -0.06
     Grund
    -0.06
     Numerous
    -0.06
    POSITIVE LOGITS
     vardır
    0.06
     versch
    0.06
    _G
    0.06
     devuelve
    0.06
    ],$
    0.06
    .Local
    0.06
     lokal
    0.06
    _Load
    0.06
    GLOBALS
    0.06
    .pushButton
    0.06
    Act Density 0.207%

    No Known Activations