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

    Neuronpedia

    INDEX
    Explanations

    evaluative comments about experiences, particularly in a dining or entertainment context

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

    Positive reviews and sentiments

    np_acts-logits-general · gemini-2.0-flash

    positive sentiment and value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndGlobalSection
    -0.72
    routeProvider
    -0.70
    脚注の使い方
    -0.65
    __':
    -0.62
    __":
    -0.61
    AddTagHelper
    -0.59
    ErrUnexpectedEOF
    -0.58
    ConstraintMaker
    -0.58
    UnsafeEnabled
    -0.58
    最快更新
    -0.57
    POSITIVE LOGITS
    Very
    0.60
    Nice
    0.58
    👌
    0.57
     👍
    0.57
     Excellent
    0.55
     matron
    0.53
     Nice
    0.53
     Very
    0.53
    👍
    0.52
    Excellent
    0.52
    Act Density 0.031%

    No Known Activations