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

    Neuronpedia

    INDEX
    Explanations

    references to news organizations and media outlets

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

    Corin Dann

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    舺
    -0.39
    arrer
    -0.36
    丰富
    -0.36
     Cha
    -0.35
    ATURES
    -0.35
    뉜
    -0.35
     Utama
    -0.35
     Grüsse
    -0.35
     Alem
    -0.34
     Eng
    -0.34
    POSITIVE LOGITS
     autorytatywna
    0.68
    ❋
    0.65
     Normdatei
    0.64
     RISERVATA
    0.57
     TestBed
    0.57
    principalColumn
    0.51
    XmlAccessorType
    0.49
    enderror
    0.48
     OMITBAD
    0.47
    LookAnd
    0.47
    Act Density 0.003%

    No Known Activations