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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting cues, particularly colons and quotation marks, possibly indicating titles or dialogue within the text

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

    user inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.52
     ProtoMessage
    -0.50
     للمعارف
    -0.47
    twimg
    -0.45
     المعيارى
    -0.43
    VYMaps
    -0.42
    postsleuth
    -0.42
     invokingState
    -0.41
     Normdatei
    -0.41
     GenerationType
    -0.40
    POSITIVE LOGITS
    UARIO
    0.46
    BASEPATH
    0.44
    rollup
    0.42
     words
    0.42
     balik
    0.42
     חיצוניים
    0.42
     mots
    0.41
    Tikang
    0.41
    pedes
    0.41
    CONFIGURATION
    0.41
    Act Density 0.075%

    No Known Activations