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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .'"↵↵
    -0.07
    Facebook
    -0.06
     اک
    -0.06
    ốc
    -0.06
    'id
    -0.06
     navy
    -0.06
     Standard
    -0.06
    _stream
    -0.06
    \n
    -0.06
    调查
    -0.06
    POSITIVE LOGITS
     parm
    0.07
     magistrate
    0.06
     geschichten
    0.06
     checkpoints
    0.06
    Alamat
    0.06
    viol
    0.06
     Muham
    0.06
    uição
    0.06
    часно
    0.06
    Nich
    0.06
    Act Density 0.002%

    No Known Activations