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

    Neuronpedia

    INDEX
    Explanations

    terms related to the appearance and features of mathematical constructs or functions

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

    appearing in text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.40
     Hintergrund
    -0.37
     Experten
    -0.34
    醐
    -0.33
     unteren
    -0.33
    ⅘
    -0.31
     Zeilen
    -0.31
     Vorteil
    -0.31
     Madsen
    -0.31
     Zweck
    -0.30
    POSITIVE LOGITS
    appearing
    0.69
     appearing
    0.68
     appeared
    0.66
     الرياضيه
    0.66
    appear
    0.66
     appear
    0.64
    appears
    0.63
    appeared
    0.62
    登場
    0.61
     appearances
    0.61
    Act Density 0.047%

    No Known Activations