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

    Neuronpedia

    INDEX
    Explanations

    solve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    愁
    -0.08
     numberOf
    -0.07
    (classes
    -0.07
     الث
    -0.07
    ホ
    -0.07
    ,num
    -0.07
    汹
    -0.07
    뻐
    -0.07
    害羞
    -0.07
    骂
    -0.06
    POSITIVE LOGITS
    돤
    0.08
    名牌
    0.07
    .Part
    0.07
    ait
    0.07
    绋
    0.07
    систем
    0.07
    iales
    0.06
     enim
    0.06
    怿
    0.06
    使劲
    0.06
    Act Density 0.016%

    No Known Activations