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

    Neuronpedia

    INDEX
    Explanations

    .write

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⎼
    -0.08
    看到
    -0.08
    쩝
    -0.07
     ví
    -0.07
     Naruto
    -0.07
     handful
    -0.07
     registro
    -0.07
    食べ
    -0.07
    hape
    -0.06
     gunshot
    -0.06
    POSITIVE LOGITS
     prejudices
    0.07
     script
    0.07
    ressing
    0.07
    ('\\
    0.07
    喉
    0.07
     characters
    0.07
    انب
    0.07
    隐
    0.07
    探访
    0.07
     bands
    0.07
    Act Density 0.002%

    No Known Activations