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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rnd
    -0.07
     wagon
    -0.07
    _az
    -0.07
     ConsoleColor
    -0.06
     verz
    -0.06
     люди
    -0.06
     Zoom
    -0.06
    _W
    -0.06
    global
    -0.06
    slaught
    -0.06
    POSITIVE LOGITS
    เศษ
    0.07
    必要
    0.07
    値
    0.07
    idae
    0.07
    lique
    0.06
    neum
    0.06
    typename
    0.06
    ")!=
    0.06
    hin
    0.06
    าหาร
    0.06
    Act Density 0.029%

    No Known Activations