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

    Neuronpedia

    INDEX
    Explanations

    Option

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .AsyncTask
    -0.08
    ů
    -0.07
     eyebrow
    -0.07
     př
    -0.07
    ュ
    -0.07
    Dallas
    -0.07
     ty
    -0.07
     grandson
    -0.07
     ברשת
    -0.07
    陸
    -0.07
    POSITIVE LOGITS
    �
    0.08
    .records
    0.08
     Overs
    0.07
     mechanically
    0.07
    highest
    0.07
     Oscar
    0.07
    cheme
    0.07
    _messages
    0.07
    开
    0.07
    一条
    0.07
    Act Density 0.005%

    No Known Activations