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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve conjunctions and qualifiers in complex sentences

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

    and connecting concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.82
    complexContent
    -0.73
     gynhyrchwyd
    -0.66
    PyExc
    -0.65
    /**
    -0.62
     iconTwitter
    -0.59
    şört
    -0.58
    <?
    -0.57
     oprot
    -0.57
    featureID
    -0.57
    POSITIVE LOGITS
    hésite
    0.38
     Sha
    0.38
    tvguidetime
    0.38
    inheritdoc
    0.33
     contrasted
    0.33
    masalahan
    0.32
    stateProvider
    0.31
     Landwir
    0.31
    SafeAreaView
    0.31
     year
    0.30
    Act Density 0.542%

    No Known Activations