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

    Neuronpedia

    INDEX
    Explanations

    file system metadata

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _word
    -0.07
     pronto
    -0.07
     Belle
    -0.07
     Ric
    -0.06
     Granny
    -0.06
    Sem
    -0.06
    APPED
    -0.06
    TouchEvent
    -0.06
    一个人
    -0.06
    _spec
    -0.06
    POSITIVE LOGITS
     Baba
    0.06
     administr
    0.06
    Pro
    0.06
     ayrıntı
    0.06
    ],
↵
    0.06
    YT
    0.06
     】
    0.06
    _fill
    0.06
     crypt
    0.06
    pro
    0.06
    Act Density 0.006%

    No Known Activations