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

    Neuronpedia

    INDEX
    Explanations

    GitHub repositories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wilde
    -0.08
    лот
    -0.07
    _errors
    -0.07
     Addiction
    -0.07
     neuroscience
    -0.07
    -interest
    -0.07
     Learning
    -0.06
    است
    -0.06
    issenschaft
    -0.06
    Monitor
    -0.06
    POSITIVE LOGITS
    DataAdapter
    0.06
    SHARE
    0.06
    �
    0.06
     रन
    0.06
    bor
    0.06
     toplantı
    0.06
     přibliž
    0.06
    PLAY
    0.06
    peq
    0.06
     zas
    0.06
    Act Density 0.230%

    No Known Activations