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

    Neuronpedia

    INDEX
    Explanations

    book synopses/reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    徙
    -0.07
    春风
    -0.07
    撤离
    -0.06
    国际贸易
    -0.06
    ività
    -0.06
    地貌
    -0.06
    ido
    -0.06
    input
    -0.06
     inventory
    -0.06
    Transformer
    -0.06
    POSITIVE LOGITS
    ˸
    0.08
    PBS
    0.07
    _SCHED
    0.07
     wegen
    0.07
    _RANK
    0.07
     Ow
    0.07
     neben
    0.07
    llvm
    0.06
     blond
    0.06
    ﰿ
    0.06
    Act Density 0.029%

    No Known Activations