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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beck
    -0.07
     Equal
    -0.06
     stylish
    -0.06
    民主
    -0.06
     Oktober
    -0.06
     предпол
    -0.06
     magnificent
    -0.06
     RIGHT
    -0.06
     Penny
    -0.06
    ahr
    -0.06
    POSITIVE LOGITS
     Delegate
    0.07
     receipts
    0.07
    "|
    0.06
     پرونده
    0.06
    dff
    0.06
    сыл
    0.06
    342
    0.06
    Якщо
    0.06
    amsung
    0.06
     defining
    0.06
    Act Density 0.008%

    No Known Activations