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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    The neuron responds to HTML tag attributes (e.g. the sequence of attribute names like class or href followed by ="…").

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	expect
    -0.07
     ext
    -0.07
    chest
    -0.06
    レイ
    -0.06
    82
    -0.06
    一年
    -0.06
    сот
    -0.06
     await
    -0.06
     immunity
    -0.06
    ariant
    -0.06
    POSITIVE LOGITS
    (MouseEvent
    0.07
    DataExchange
    0.06
     cdr
    0.06
    _EXEC
    0.06
     CascadeType
    0.06
     Fam
    0.06
     DataAccess
    0.06
    _OPTION
    0.06
    .persist
    0.06
     FieldType
    0.06
    Act Density 0.004%

    No Known Activations