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

    Neuronpedia

    INDEX
    Explanations

    words related to limitations or conditions on availability

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

    only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.51
     informací
    -0.47
    geführten
    -0.46
     informée
    -0.45
    IntoConstraints
    -0.44
     cappuccio
    -0.44
     poroz
    -0.42
     olev
    -0.41
    がございます
    -0.41
    čných
    -0.41
    POSITIVE LOGITS
     Только
    0.69
    Только
    0.64
    ább
    0.57
    poň
    0.57
     незавершена
    0.57
    jmniej
    0.57
    ільки
    0.55
     ویکی‌پدی
    0.54
     tylko
    0.53
    только
    0.52
    Act Density 0.005%

    No Known Activations