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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables within technical or scientific contexts

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

    Mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.46
    urro
    -0.45
    不止
    -0.45
    <eos>
    -0.43
     입
    -0.41
    입
    -0.40
     L
    -0.39
    ף
    -0.39
     berhenti
    -0.39
     A
    -0.38
    POSITIVE LOGITS
     itſelf
    0.86
    CloseOperation
    0.85
     оригіналу
    0.85
     дописавши
    0.84
     كومونز
    0.82
     مشين
    0.78
     pleaſure
    0.77
     nakalista
    0.77
     ContentValues
    0.75
     мәкал
    0.75
    Act Density 1.065%

    No Known Activations