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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate guidance or recommendations for users

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.46
    arakhand
    -0.44
    ↵↵
    -0.44
    appspot
    -0.43
    apikey
    -0.41
    */
    -0.41
    ácara
    -0.41
     inaugu
    -0.40
    appName
    -0.40
    icestershire
    -0.39
    POSITIVE LOGITS
    OCCURRED
    0.62
     avoient
    0.59
     فريبيس
    0.58
     שוליים
    0.56
     semelh
    0.54
     gustó
    0.54
    IntoConstraints
    0.53
    depuis
    0.53
    tangentMode
    0.52
     nothwendig
    0.52
    Act Density 0.035%

    No Known Activations