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

    Neuronpedia

    INDEX
    Explanations

    Supply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ttt
    1.00
    ँग
    0.91
    jango
    0.90
    𝘭
    0.90
    AnimationStyle
    0.87
     kik
    0.87
    ttle
    0.86
    бла
    0.86
     skut
    0.85
     afet
    0.84
    POSITIVE LOGITS
     dotato
    0.91
    rocyte
    0.79
     অব্যাহত
    0.78
     Faust
    0.77
     tavolo
    0.76
     Continuando
    0.75
     받아
    0.75
     ricerca
    0.74
     situé
    0.74
     Соб
    0.73
    Act Density 0.001%

    No Known Activations