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

    Neuronpedia

    INDEX
    Explanations

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Emo
    0.41
    Risk
    0.39
    elaar
    0.39
    E
    0.38
     گروه
    0.38
     لكن
    0.38
     وصول
    0.38
    摸
    0.38
    Texas
    0.38
    Daily
    0.37
    POSITIVE LOGITS
     chac
    0.54
    ಣಿ
    0.52
    7
    0.52
    6
    0.51
    4
    0.50
     titular
    0.50
    냐면
    0.47
    س
    0.47
    5
    0.46
     quantization
    0.46
    Act Density 0.007%

    No Known Activations