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

    Neuronpedia

    INDEX
    Explanations

    Duty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ächst
    -0.07
     양
    -0.07
     persons
    -0.06
    ,temp
    -0.06
    osas
    -0.06
     convers
    -0.06
    765
    -0.06
    744
    -0.06
    esso
    -0.06
    ечно
    -0.06
    POSITIVE LOGITS
    ':{'
    0.07
     Duty
    0.06
    ?):
    0.06
     clickable
    0.06
    /datatables
    0.06
     imaginative
    0.06
    าษฎ
    0.06
     لی
    0.06
    ี้↵
    0.06
     недостат
    0.06
    Act Density 0.002%

    No Known Activations