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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in textual data

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

    Numbers followed by "item(s)" or "elements"

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units or counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consultato
    -0.48
     InputDecoration
    -0.47
    Ainda
    -0.47
    jectory
    -0.47
    tvguidetime
    -0.47
    ContentLoaded
    -0.47
    -0.46
    splash
    -0.46
    hauled
    -0.45
     discography
    -0.45
    POSITIVE LOGITS
    fjspx
    0.75
    tagHelperRunner
    0.60
     stuks
    0.59
    SourceChecksum
    0.56
    AutoScaleMode
    0.56
    addCriterion
    0.56
     одновременно
    0.55
    mybatisplus
    0.54
    UrlResolution
    0.53
    ufig
    0.51
    Act Density 0.340%

    No Known Activations