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

    Neuronpedia

    INDEX
    Explanations

    phrases questioning actions or activities

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

    what am i doing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Decke
    -0.42
     arcilla
    -0.42
     comigo
    -0.41
     borboleta
    -0.40
     extracción
    -0.39
     propOrder
    -0.39
     révé
    -0.39
     Anzeige
    -0.39
    retudo
    -0.39
     preuves
    -0.38
    POSITIVE LOGITS
    antMatchers
    0.65
    WriteTagHelper
    0.63
    发表于
    0.63
    ScopeManager
    0.57
    RenderAtEndOf
    0.56
    DllImport
    0.55
    aarrggbb
    0.54
    Билгалдахарш
    0.54
    rrggbb
    0.52
     שוליים
    0.52
    Act Density 0.022%

    No Known Activations