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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bunk
    -0.07
    人类
    -0.07
    たら
    -0.06
    책
    -0.06
     empres
    -0.06
     ارتباط
    -0.06
     requires
    -0.06
     аналіз
    -0.06
    Coords
    -0.06
     Hoffman
    -0.06
    POSITIVE LOGITS
    roker
    0.08
     clearInterval
    0.07
    .checkBox
    0.07
    agner
    0.07
    _DROP
    0.06
    .ReadString
    0.06
    ollectors
    0.06
    _ROM
    0.06
    arer
    0.06
     ор
    0.06
    Act Density 0.006%

    No Known Activations