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

    Neuronpedia

    INDEX
    Explanations

    programming syntax elements and punctuation in code snippets

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

    ends user inputs with comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.62
     EconPapers
    -0.59
    Datuak
    -0.57
    称
    -0.56
    الحياه
    -0.55
    Билгалдахарш
    -0.55
    verwijspagina
    -0.54
    المكان
    -0.54
    awaiter
    -0.53
    évaluateur
    -0.51
    POSITIVE LOGITS
    ſt
    0.41
     pleaſure
    0.40
    //
    0.38
     houſe
    0.38
    IntoConstraints
    0.36
    paravant
    0.36
     armées
    0.34
    gonic
    0.34
     dieux
    0.34
     heureuse
    0.34
    Act Density 0.168%

    No Known Activations