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

    Neuronpedia

    INDEX
    Explanations

    missing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :not
    -0.07
     教
    -0.07
    _field
    -0.07
     będ
    -0.06
     Talk
    -0.06
     parler
    -0.06
     itemName
    -0.06
    >}
    -0.06
     Reporter
    -0.06
    /table
    -0.06
    POSITIVE LOGITS
    /WebAPI
    0.07
    ss
    0.06
    公开
    0.06
    leine
    0.06
     seu
    0.06
    최고
    0.06
     mism
    0.06
    NSE
    0.06
    /{
    0.05
     хвилин
    0.05
    Act Density 0.001%

    No Known Activations