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

    Neuronpedia

    INDEX
    Explanations

    Quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liability
    -0.07
    types
    -0.07
     recently
    -0.07
     geliş
    -0.06
    -In
    -0.06
     worse
    -0.06
     liability
    -0.06
    files
    -0.06
     timp
    -0.06
    _node
    -0.06
    POSITIVE LOGITS
    寒
    0.07
     рес
    0.06
     vys
    0.06
    isex
    0.06
     Fashion
    0.06
    (find
    0.06
     �
    0.06
    .toJson
    0.06
    мет
    0.06
    ุษย
    0.06
    Act Density 0.008%

    No Known Activations