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

    Neuronpedia

    INDEX
    Explanations

    chema

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Assign
    -0.07
    Atlas
    -0.07
     emblem
    -0.07
    需要注意
    -0.07
     handy
    -0.06
    intersect
    -0.06
     بالن
    -0.06
    协会
    -0.06
     interpret
    -0.06
     Tips
    -0.06
    POSITIVE LOGITS
     onwards
    0.07
    围墙
    0.07
    _FREQUENCY
    0.07
    _Base
    0.07
     Roulette
    0.07
    洴
    0.07
    IVE
    0.07
    ète
    0.07
    FAIL
    0.07
    _SENS
    0.07
    Act Density 0.003%

    No Known Activations