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

    Neuronpedia

    INDEX
    Explanations

    references to proper procedures and standards

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

    Preceding words for "way", "answer", "jury", "instruction", "thing"

    np_acts-logits-general · gemini-2.0-flash

    proper and correct usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    excellents
    -0.57
    JspWriter
    -0.57
    InjectAttribute
    -0.57
    RectangleBorder
    -0.54
     erfolgreich
    -0.51
    convenience
    -0.51
     الاطلاع
    -0.51
    ⓧ
    -0.51
     exitoso
    -0.51
    awtextra
    -0.49
    POSITIVE LOGITS
     timing
    0.71
     sized
    0.70
    tied
    0.66
     mix
    0.65
     proportions
    0.64
     Mischung
    0.63
     balance
    0.63
     Zeitpunkt
    0.63
     combination
    0.62
     réponse
    0.61
    Act Density 0.350%

    No Known Activations