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

    Neuronpedia

    INDEX
    Explanations

    gain and weight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    цыя
    0.39
    ষেধ
    0.39
     Licenses
    0.37
     яви
    0.37
    чется
    0.35
    िवर्स
    0.35
    тился
    0.35
     Licence
    0.35
    梓
    0.34
    ྪ
    0.34
    POSITIVE LOGITS
     gain
    4.38
     Gain
    3.97
     gains
    3.86
    Gain
    3.86
     gaining
    3.84
     gained
    3.78
    gain
    3.78
     Gains
    3.38
     gan
    2.98
     ganhar
    2.91
    Act Density 0.079%

    No Known Activations