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

    Neuronpedia

    INDEX
    Explanations

    many languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taste
    -0.07
    hots
    -0.06
    在意
    -0.06
    oling
    -0.06
    Aggregate
    -0.06
     entering
    -0.06
     composing
    -0.06
    _TIMEOUT
    -0.06
    Named
    -0.06
    夏
    -0.06
    POSITIVE LOGITS
    发病率
    0.07
     활
    0.07
     "',
    0.06
    (EFFECT
    0.06
     dgv
    0.06
    늪
    0.06
    锫
    0.06
    局势
    0.06
    鞅
    0.06
    같
    0.06
    Act Density 0.134%

    No Known Activations