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

    Neuronpedia

    INDEX
    Explanations

    pushing limits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fake
    -0.07
    timeline
    -0.07
    рест
    -0.07
    З
    -0.06
     ngx
    -0.06
     množství
    -0.06
     tổn
    -0.06
    $j
    -0.06
     корпус
    -0.06
     вы
    -0.06
    POSITIVE LOGITS
    )、
    0.07
     فه
    0.07
     neby
    0.07
    _processors
    0.06
    žit
    0.06
     ketogenic
    0.06
     lever
    0.06
     bend
    0.06
    .Struct
    0.06
    \\\
    0.06
    Act Density 0.018%

    No Known Activations