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

    Neuronpedia

    INDEX
    Explanations

    instances of conflict and moral dilemmas involving characters

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

    Follows a capital letter

    np_acts-logits-general · gemini-2.0-flash

    hero names and quirks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.64
     VizieR
    -0.59
    WebElementEntity
    -0.57
    Controllo
    -0.52
     utafitiHapana
    -0.50
     defaultstate
    -0.49
     cubanos
    -0.48
    WebControls
    -0.48
    قى
    -0.45
     JSTOR
    -0.45
    POSITIVE LOGITS
     All
    0.82
     Mid
    0.79
     Tod
    0.77
    Dek
    0.75
     hero
    0.75
     quirk
    0.75
     Dek
    0.74
     Baku
    0.74
     Izuku
    0.74
     Kac
    0.73
    Act Density 0.082%

    No Known Activations