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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and character names in narratives

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

    My Hero Academia characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.68
    دانشنامهٔ
    -0.67
    verwijspagina
    -0.66
    الحياه
    -0.63
    Tikang
    -0.60
     الحره
    -0.58
     Vikipedi
    -0.57
     Wiktionnaire
    -0.56
    principalTable
    -0.56
     ddelweddau
    -0.55
    POSITIVE LOGITS
    MessageTagHelper
    0.41
     Geschichts
    0.35
    цездатний
    0.35
     larmes
    0.34
     enfans
    0.33
    translates
    0.31
     madeira
    0.31
     Geruch
    0.29
     ſte
    0.29
    zustellen
    0.28
    Act Density 0.020%

    No Known Activations