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

    Neuronpedia

    INDEX
    Explanations

    conditionality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pry
    -0.06
    _db
    -0.06
    рип
    -0.06
    EY
    -0.06
     Jah
    -0.06
     Coh
    -0.06
     Ah
    -0.06
     cops
    -0.06
    Lim
    -0.06
    ümü
    -0.06
    POSITIVE LOGITS
    .Compile
    0.08
    施
    0.07
     Trainer
    0.07
     QIcon
    0.06
     sluts
    0.06
     onSelect
    0.06
    .Translate
    0.06
     Street
    0.06
     reason
    0.06
    fault
    0.06
    Act Density 0.073%

    No Known Activations