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

    Neuronpedia

    INDEX
    Explanations

    hypothesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Semantic
    -0.07
    pedido
    -0.06
    宮
    -0.06
     compass
    -0.06
     tow
    -0.06
     компанії
    -0.06
     trademark
    -0.06
     장
    -0.06
     joy
    -0.06
    _Level
    -0.06
    POSITIVE LOGITS
    ALSE
    0.07
    'є
    0.07
    issance
    0.07
     psik
    0.07
    زار
    0.06
    .xls
    0.06
    ."','".$
    0.06
    IF
    0.06
    endas
    0.06
    ,out
    0.06
    Act Density 0.009%

    No Known Activations