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

    Neuronpedia

    INDEX
    Explanations

    detailed explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offset
    0.81
     boost
    0.80
    offset
    0.76
     Offset
    0.74
     contrast
    0.70
    泞
    0.66
     buoy
    0.65
    sometimes
    0.65
    Offset
    0.65
     post
    0.64
    POSITIVE LOGITS
    ようやく
    0.88
    详细
    0.86
     ሁሉ
    0.85
    詳細
    0.85
     كامل
    0.84
     കൃ
    0.84
    全面的
    0.84
    كامل
    0.84
     completamente
    0.84
     بدأ
    0.83
    Act Density 0.184%

    No Known Activations