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

    Neuronpedia

    INDEX
    Explanations

    return statements in code snippets

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

    function return statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.81
    GEBURTSDATUM
    -0.77
    Datuak
    -0.74
    WebElementEntity
    -0.70
    protoimpl
    -0.70
    Aholisi
    -0.69
     TextAppearance
    -0.67
     Италијани
    -0.66
     للاسماء
    -0.66
    elemField
    -0.65
    POSITIVE LOGITS
    (
    0.36
     intellectuelle
    0.32
     the
    0.30
    return
    0.27
     Jerusalén
    0.26
     médicale
    0.26
     écrite
    0.25
     magnétique
    0.25
     rumput
    0.25
     dziewczyn
    0.24
    Act Density 0.015%

    No Known Activations