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

    Neuronpedia

    INDEX
    Explanations

    language mixing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     macro
    0.45
    dynam
    0.45
     consonant
    0.44
     consonants
    0.44
    d
    0.43
     heller
    0.43
     ग्राह
    0.42
     catalysts
    0.42
     currents
    0.41
     catechol
    0.41
    POSITIVE LOGITS
    ಮ್ಮ
    0.48
    问道
    0.45
    şam
    0.44
    дума
    0.44
    Duz
    0.43
    ﺫ
    0.43
    த்து
    0.43
     sayı
    0.43
    考えて
    0.42
     Nasıl
    0.41
    Act Density 0.001%

    No Known Activations