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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the structure and format of a document or text

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

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.81
     <<<<<<<<<<<<<<
    -0.71
     kasarigan
    -0.70
    Geplaatst
    -0.68
    SuspendLayout
    -0.66
    iſchen
    -0.65
    ſicht
    -0.65
    enumii
    -0.65
     snippetHide
    -0.64
    ſſung
    -0.64
    POSITIVE LOGITS
    elesaikan
    0.35
     infancia
    0.34
     connaissances
    0.34
     mitään
    0.32
     enfance
    0.32
     allmän
    0.32
     Kindheit
    0.32
     civilización
    0.32
     savons
    0.32
     descripción
    0.31
    Act Density 0.365%

    No Known Activations