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

    Neuronpedia

    INDEX
    Explanations

    Mug

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debut
    -0.07
    -------
    -0.06
    数字
    -0.06
    eways
    -0.06
     Initializing
    -0.06
    าของ
    -0.06
     cmake
    -0.06
    -',
    -0.06
    似乎
    -0.06
    WSC
    -0.06
    POSITIVE LOGITS
     μετα
    0.08
    urgeon
    0.07
    持
    0.07
    (Media
    0.07
     Mp
    0.06
     vypl
    0.06
     Gregg
    0.06
    mpr
    0.06
     kâ
    0.06
     tarn
    0.06
    Act Density 0.001%

    No Known Activations