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

    Neuronpedia

    INDEX
    Explanations

    Pyramid Song

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     we
    0.41
     siamo
    0.40
     fires
    0.40
     দিবে
    0.40
     azione
    0.39
     artista
    0.38
    我们
    0.38
    ्ञ
    0.38
     arriba
    0.38
     我们
    0.37
    POSITIVE LOGITS
    onom
    0.44
    annie
    0.40
    VCTarget
    0.39
    intera
    0.38
    intage
    0.38
    ResponseWriter
    0.38
    unread
    0.37
    inski
    0.37
     capas
    0.36
     अत्या
    0.36
    Act Density 0.000%

    No Known Activations