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

    Neuronpedia

    INDEX
    Explanations

    references to scholarly works and citations

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

    URLs and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     telefónica
    -0.34
     gay
    -0.31
     fidanz
    -0.31
     over
    -0.29
     successful
    -0.29
     وو
    -0.28
    EROUS
    -0.27
    simas
    -0.27
    b
    -0.27
     educational
    -0.27
    POSITIVE LOGITS
     Италијани
    0.92
     незавершена
    0.82
    تقاوى
    0.79
    Personensuche
    0.78
    GEBURTSDATUM
    0.77
     nakalista
    0.75
     tartalomajánló
    0.73
     Мексичка
    0.71
    adaptiveStyles
    0.71
     otomatig
    0.71
    Act Density 0.005%

    No Known Activations