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

    Neuronpedia

    INDEX
    Explanations

    quantities and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eventType
    0.41
    vartheta
    0.40
     жа
    0.39
     संबोध
    0.38
     deviate
    0.38
    altungen
    0.38
    мога
    0.37
     સંદેશ
    0.37
     જા
    0.37
     narration
    0.37
    POSITIVE LOGITS
    一副
    0.40
    串
    0.39
    itute
    0.38
    unoscut
    0.38
     çant
    0.38
    誰
    0.37
    一身
    0.37
     scarf
    0.37
    otch
    0.37
    Fechar
    0.37
    Act Density 0.001%

    No Known Activations