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

    Neuronpedia

    INDEX
    Explanations

    .net

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cheers
    0.76
    Cheers
    0.66
    置いて
    0.62
     den
    0.60
     Equation
    0.59
     completely
    0.59
     Den
    0.58
     ainsi
    0.58
     Des
    0.58
     transm
    0.57
    POSITIVE LOGITS
     INumber
    0.89
    ለሁ
    0.84
     アイ
    0.83
    iflix
    0.78
     Mientras
    0.77
    弟子
    0.77
    oconut
    0.76
    ɨ
    0.75
     هال
    0.73
     IJ
    0.73
    Act Density 0.170%

    No Known Activations