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

    Neuronpedia

    INDEX
    Explanations

    creating new text rather than retrieving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tyrannical
    0.84
    spark
    0.82
    ip
    0.81
    tod
    0.78
    控
    0.77
    presumably
    0.75
     publicación
    0.74
    epis
    0.74
     detalles
    0.73
    exo
    0.72
    POSITIVE LOGITS
     aspire
    0.73
     கரி
    0.72
     defaults
    0.72
     ณ
    0.71
     สี
    0.70
     header
    0.67
     aflat
    0.66
     at
    0.65
     overlays
    0.65
     x
    0.64
    Act Density 0.005%

    No Known Activations