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

    Neuronpedia

    INDEX
    Explanations

    symbols, punctuation, and formatting indicators commonly used in dialogue or text representations

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

    dialogue markers and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.67
     مشين
    -0.61
     <<<<<<<<<<<<<<
    -0.59
     للمعارف
    -0.58
    存于互联网档案馆
    -0.53
    porn
    -0.49
    rungsseite
    -0.48
     porn
    -0.46
     Porn
    -0.45
     noqa
    -0.45
    POSITIVE LOGITS
    EDEFAULT
    0.52
     libremente
    0.47
     contextLoads
    0.47
     gynhyrchwyd
    0.43
    MigrationBuilder
    0.40
     Comprometido
    0.40
     yoksa
    0.38
     Wicidata
    0.37
    țional
    0.36
     librement
    0.36
    Act Density 0.136%

    No Known Activations