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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or conditionals

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

    whether or no matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Välislingid
    -0.53
    ()?;
    -0.52
    addCriterion
    -0.46
     ***!
    -0.46
    rungsseite
    -0.46
     *++
    -0.44
    yorlar
    -0.43
    /*
    -0.42
    EndGlobalSection
    -0.40
     iprot
    -0.39
    POSITIVE LOGITS
     كومونز
    0.55
    évaluateur
    0.47
     électron
    0.45
     EconPapers
    0.42
    TextUtils
    0.41
     HttpStatusCode
    0.41
    TRAILING
    0.40
    seitig
    0.39
    nalités
    0.39
    ientôt
    0.39
    Act Density 0.009%

    No Known Activations