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

    Neuronpedia

    INDEX
    Explanations

    specific pronouns, auxiliary verbs, and common sentence structures that indicate dialogue and interaction

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

    what starts a question or narrative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.73
     للمعارف
    -0.66
     doInBackground
    -0.60
    parsedMessage
    -0.60
    writeFieldEnd
    -0.59
     للاسماء
    -0.58
    Parcelize
    -0.57
    sizeCache
    -0.53
     فريبيس
    -0.52
    verifyException
    -0.50
    POSITIVE LOGITS
    tagext
    0.44
    Writers
    0.34
     Writers
    0.33
    énario
    0.33
     droplets
    0.32
     finish
    0.31
     finished
    0.30
     Liebes
    0.30
    Autoritní
    0.30
     escena
    0.29
    Act Density 0.001%

    No Known Activations