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

    Neuronpedia

    INDEX
    Explanations

    fast, fastify, fair, speech, chat, ai

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آه
    0.42
    ROTTLE
    0.41
    Tart
    0.40
    izacji
    0.40
     நம்
    0.39
    Fund
    0.39
    ږئ
    0.39
    Sob
    0.39
    фикации
    0.39
    蓣
    0.39
    POSITIVE LOGITS
     FA
    0.56
     FAS
    0.54
     Fa
    0.52
    idious
    0.50
     FAT
    0.50
     fa
    0.48
     ഫാ
    0.48
     Fass
    0.48
     FAST
    0.47
     Fas
    0.46
    Act Density 0.036%

    No Known Activations