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

    Neuronpedia

    INDEX
    Explanations

    rule about divisibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    0.86
    ين
    0.70
    ско
    0.70
    imagem
    0.67
    он
    0.66
    𝘨
    0.66
    p
    0.65
    ິ
    0.65
    𝘰
    0.64
     tension
    0.63
    POSITIVE LOGITS
    .'
    0.76
     которым
    0.75
     obliterated
    0.75
    ’
    0.75
     contiene
    0.75
     Krankheit
    0.75
     dhatu
    0.75
     poised
    0.74
     PDEs
    0.74
    슥
    0.73
    Act Density 0.004%

    No Known Activations