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

    Neuronpedia

    INDEX
    Explanations

    references to heroes in various contexts

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

    heroes or superheroes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.55
     kasarigan
    -0.46
    OGND
    -0.44
    RTGC
    -0.43
    LabelTagHelper
    -0.43
    исленность
    -0.43
    giar
    -0.42
     Administrativna
    -0.40
    참고
    -0.40
     opdracht
    -0.39
    POSITIVE LOGITS
     Heroes
    2.27
    Heroes
    2.22
    heroes
    2.08
     heroes
    1.92
    HERO
    1.38
     HERO
    1.38
     héroes
    1.24
    Hero
    1.23
    hero
    1.22
     Hero
    1.15
    Act Density 0.001%

    No Known Activations