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

    Neuronpedia

    INDEX
    Explanations

    instances of quoted speech or dialogue

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

    dialogue opening punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.63
     faſt
    -0.63
     ſta
    -0.60
     ſur
    -0.58
     beſ
    -0.57
     ſte
    -0.55
     unſ
    -0.54
     ſtate
    -0.54
    ſelf
    -0.53
     obſ
    -0.53
    POSITIVE LOGITS
    Geplaatst
    0.42
    MemoryWarning
    0.41
    AnimationsModule
    0.41
     الرخصة
    0.38
     创建时间
    0.37
    UpInside
    0.37
    Vorlage
    0.37
    ะ
    0.36
    HtmlAttribute
    0.36
    asgi
    0.36
    Act Density 0.002%

    No Known Activations