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

    Neuronpedia

    INDEX
    Explanations

    explanation of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uiteindelijk
    0.47
    ેચ્છ
    0.44
     Almighty
    0.41
    った
    0.41
    ystyrene
    0.41
    IList
    0.40
    全身
    0.40
     ModInt
    0.40
    んでいます
    0.40
     الدراسي
    0.40
    POSITIVE LOGITS
     about
    1.13
     regarding
    1.13
     tentang
    1.09
     về
    1.09
    关于
    1.04
     mengenai
    0.98
    關於
    0.91
    regarding
    0.91
     щодо
    0.88
     acerca
    0.87
    Act Density 1.060%

    No Known Activations