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

    Neuronpedia

    INDEX
    Explanations

    made

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    다가
    -0.07
     ------
    -0.07
    Plugins
    -0.06
    ，我们
    -0.06
     unmatched
    -0.06
     Wer
    -0.06
    кав
    -0.06
     excit
    -0.06
     =(
    -0.06
     الوقت
    -0.06
    POSITIVE LOGITS
    приєм
    0.07
    PLE
    0.06
    チュ
    0.06
    ुओ
    0.06
    ,p
    0.06
    ышлен
    0.06
    receive
    0.06
    OPS
    0.06
    rench
    0.06
    _WEEK
    0.06
    Act Density 0.002%

    No Known Activations