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

    Neuronpedia

    INDEX
    Explanations

    terms related to detection processes and methodologies

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

    detection methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perſon
    -0.57
     *++
    -0.54
     $_(
    -0.54
     fevere
    -0.54
    andas
    -0.54
    LayoutParams
    -0.53
    Paragraph
    -0.52
     Verſ
    -0.52
    ufficio
    -0.51
     Anſ
    -0.51
    POSITIVE LOGITS
     detection
    1.98
     Detection
    1.91
    detection
    1.73
    Detection
    1.72
     DETECTION
    1.43
     detections
    1.29
     detección
    1.14
     detecting
    1.09
     detect
    1.06
     detec
    1.06
    Act Density 0.016%

    No Known Activations