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

    Neuronpedia

    INDEX
    Explanations

    Lumber measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     آزادی
    -0.08
     Umwelt
    -0.08
     جاری
    -0.08
     milieu
    -0.08
    蜜
    -0.07
    奖励
    -0.07
    cursor
    -0.07
    _DISABLE
    -0.07
     safeguard
    -0.07
     DREAM
    -0.07
    POSITIVE LOGITS
     corta
    0.10
     woodworking
    0.09
     truncated
    0.09
     perpendicular
    0.09
     peças
    0.08
     oriented
    0.08
     tapered
    0.08
     فرانس
    0.08
     shorter
    0.08
    _trim
    0.08
    Act Density 0.014%

    No Known Activations