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

    Neuronpedia

    INDEX
    Explanations

    Week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    การพ
    -0.07
     offences
    -0.07
     Rolls
    -0.07
     فو
    -0.07
    ؤال
    -0.07
     край
    -0.06
     Pulitzer
    -0.06
    ря
    -0.06
     كتاب
    -0.06
    Grey
    -0.06
    POSITIVE LOGITS
    resultado
    0.07
    >--}}↵
    0.07
    <My
    0.06
    card
    0.06
    ıldığında
    0.06
     Teens
    0.06
    _commit
    0.06
    \
↵
    0.06
     Applications
    0.06
     Moment
    0.06
    Act Density 0.004%

    No Known Activations