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

    Neuronpedia

    INDEX
    Explanations

    Credit or naming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    frey
    -0.06
    瑞
    -0.06
    н
    -0.06
     Rapid
    -0.06
    ор
    -0.06
     زنان
    -0.06
     helicopters
    -0.06
     cartridge
    -0.06
    velocity
    -0.06
    금
    -0.06
    POSITIVE LOGITS
    final
    0.07
    _POINTER
    0.07
    crawl
    0.07
    "]/
    0.06
     Luca
    0.06
    キング
    0.06
     Ки
    0.06
    .share
    0.06
    .source
    0.06
     실시
    0.06
    Act Density 0.077%

    No Known Activations