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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .section
    -0.08
    زان
    -0.07
    配
    -0.07
     allergy
    -0.07
     معمول
    -0.07
     aggregates
    -0.07
     autor
    -0.07
     Fiction
    -0.07
    ks
    -0.07
     Ft
    -0.06
    POSITIVE LOGITS
     удов
    0.09
     �
    0.07
    November
    0.06
    _Def
    0.06
    CGPoint
    0.06
    ただ
    0.06
     casually
    0.06
     điều
    0.06
     inadequate
    0.06
    Along
    0.06
    Act Density 0.001%

    No Known Activations