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

    Neuronpedia

    INDEX
    Explanations

    references to false statements or misdiagnosis in medical contexts

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

    Pluralized surnames or colors

    np_acts-logits-general · gemini-2.0-flash

    colors and names ending in 's'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decorativos
    -0.92
     motivadoras
    -0.87
     définiti
    -0.83
     financières
    -0.78
     vectoriales
    -0.78
     decorativas
    -0.77
     espirituales
    -0.77
     médicaux
    -0.75
     lèvres
    -0.74
     colorés
    -0.74
    POSITIVE LOGITS
     Davids
    0.81
     Smiths
    0.79
     Blacks
    0.79
     yellows
    0.79
     greens
    0.79
    Johns
    0.78
     Browns
    0.77
     whites
    0.77
     Whites
    0.77
     Silvers
    0.76
    Act Density 0.602%

    No Known Activations