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

    Neuronpedia

    INDEX
    Explanations

    characters and their interactions in a narrative or script

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

    proper nouns and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defined
    -0.38
     a
    -0.37
     not
    -0.36
    umenten
    -0.36
     imper
    -0.36
    ScopeManager
    -0.35
    ็จ
    -0.35
     twar
    -0.35
     share
    -0.35
    ↵↵
    -0.35
    POSITIVE LOGITS
    RenderAtEndOf
    0.69
     BoxFit
    0.58
     endwhile
    0.56
    UnitTesting
    0.55
    parsedMessage
    0.54
    postsleuth
    0.54
    CDCl
    0.53
    Parcelize
    0.53
     zijne
    0.52
     BrowserModule
    0.52
    Act Density 0.115%

    No Known Activations