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

    Neuronpedia

    INDEX
    Explanations

    talking in Indonesian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Layout
    0.75
    RefItem
    0.71
    レシピ
    0.69
    idimensional
    0.69
    amide
    0.68
     দীন
    0.68
     resur
    0.67
    뵐
    0.65
     திரைப்படம்
    0.65
    URL
    0.65
    POSITIVE LOGITS
     words
    1.16
     tegas
    1.07
     kata
    1.06
     Words
    0.99
     pap
    0.98
     tut
    0.95
     palavras
    0.94
     tutur
    0.93
     palabras
    0.91
     слова
    0.91
    Act Density 0.002%

    No Known Activations