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

    Neuronpedia

    INDEX
    Explanations

    extr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    belum
    -0.07
     agitation
    -0.07
    kou
    -0.07
    できる
    -0.06
     Storage
    -0.06
     dinheiro
    -0.06
    数字
    -0.06
     Đo
    -0.06
     спрос
    -0.06
     billionaire
    -0.06
    POSITIVE LOGITS
     Siz
    0.06
    จร
    0.06
     lust
    0.06
    .ul
    0.06
    ßer
    0.06
    зі
    0.06
     Prev
    0.06
    RetVal
    0.06
    999
    0.06
    저
    0.06
    Act Density 0.003%

    No Known Activations