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

    Neuronpedia

    INDEX
    Explanations

    repetitions or patterns in textual data

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

    code structure and control flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.51
    unschweig
    -0.47
     footh
    -0.46
    SneakyThrows
    -0.45
    StateToProps
    -0.43
    flashdata
    -0.43
    tschafts
    -0.42
    therford
    -0.42
     interesar
    -0.41
     detik
    -0.41
    POSITIVE LOGITS
    Hentet
    0.61
     للمعارف
    0.59
     autorytatywna
    0.59
    évaluateur
    0.50
     lenker
    0.47
    pexpr
    0.46
    IUrlHelper
    0.45
    rungsseite
    0.45
     Anſ
    0.44
     EconPapers
    0.44
    Act Density 0.040%

    No Known Activations