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

    Neuronpedia

    INDEX
    Explanations

    punctuation symbols, particularly periods, and high-frequency contextual words

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

    `.` followed by `on` or `then`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.74
    ymce
    -0.65
    $_['
    -0.63
    ChildScrollView
    -0.60
    kloped
    -0.60
     ModelRenderer
    -0.58
    ArgsConstructor
    -0.56
    featureID
    -0.55
     ComVisible
    -0.55
    principalTable
    -0.54
    POSITIVE LOGITS
    ⎞
    0.34
    bentar
    0.32
    EndInit
    0.32
     hiệp
    0.32
    jenige
    0.30
     fraî
    0.30
     komis
    0.30
    )}+\
    0.30
    )$}
    0.29
    <!--[
    0.29
    Act Density 0.000%

    No Known Activations