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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating methodology or processes

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

    sentence beginnings and key verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.71
    fillType
    -0.57
    存于互联网档案馆
    -0.50
    .*")]
    -0.49
    twimg
    -0.47
    gemaakt
    -0.47
    FieldBuilder
    -0.45
    xhttp
    -0.45
     strdup
    -0.44
     emailAlready
    -0.44
    POSITIVE LOGITS
     Infórmanos
    0.48
    帖最后由
    0.39
    0.38
    DispatchToProps
    0.38
    Билгалдахарш
    0.36
    violi
    0.36
    XmlAccessorType
    0.36
    ostante
    0.35
    のだろうか
    0.34
    LabelTagHelper
    0.33
    Act Density 0.109%

    No Known Activations