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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

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

    periods and code-related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "
    -0.42
     '
    -0.41
     abbraccio
    -0.40
     aforementioned
    -0.40
     experience
    -0.40
     (
    -0.39
     samfun
    -0.39
     çap
    -0.38
     apporté
    -0.38
     #
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.92
     ModelExpression
    0.74
    IntoConstraints
    0.65
    帖最后由
    0.63
    IVEREF
    0.63
    tagHelperRunner
    0.61
    WriteAttribute
    0.60
    encodeWith
    0.57
     الحره
    0.56
     noDo
    0.56
    Act Density 0.057%

    No Known Activations