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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الصحفي
    -0.06
     illustrated
    -0.06
    build
    -0.06
     acab
    -0.06
    扎
    -0.06
    mast
    -0.06
     (!_
    -0.06
    _tgt
    -0.06
     aides
    -0.06
    -bin
    -0.06
    POSITIVE LOGITS
    各種
    0.08
    _Move
    0.07
    <boolean
    0.07
    _Se
    0.07
     اله
    0.07
    国产
    0.07
     Cort
    0.07
    诡异
    0.06
    揽
    0.06
    垃圾分类
    0.06
    Act Density 0.049%

    No Known Activations