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

    Neuronpedia

    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xCF
    -0.07
    peg
    -0.06
     Horny
    -0.06
    .prof
    -0.06
    FROM
    -0.06
    :f
    -0.06
    ombre
    -0.06
    wit
    -0.06
    >Name
    -0.06
     wegen
    -0.06
    POSITIVE LOGITS
    wrapper
    0.07
    Validators
    0.06
    ریب
    0.06
    正确
    0.06
     monster
    0.06
     timeframe
    0.06
    richt
    0.06
     getSession
    0.06
    ──
    0.06
    增加
    0.06
    Act Density 0.003%

    No Known Activations