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

    Neuronpedia

    INDEX
    Explanations

    comparative metrics regarding size, prevalence, and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    highest rate or value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.49
    Pranala
    -0.44
     asesinado
    -0.42
     وعد
    -0.41
    ỡng
    -0.40
    клопе
    -0.40
     betul
    -0.40
    Réalisation
    -0.38
    DoubleQuotes
    -0.37
    ainville
    -0.37
    POSITIVE LOGITS
    sweise
    0.50
     oorsp
    0.49
    uxxxx
    0.49
    🥈
    0.47
     elif
    0.46
    )++;
    0.45
     "\<
    0.43
    elif
    0.42
     belangrijke
    0.42
    ilane
    0.42
    Act Density 0.019%

    No Known Activations