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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NCAA
    -0.08
    ournaments
    -0.08
    ander
    -0.07
    宴
    -0.07
     voyage
    -0.07
     methodological
    -0.07
     menstrual
    -0.07
     সভ
    -0.07
     tournament
    -0.07
    ighton
    -0.07
    POSITIVE LOGITS
     customers
    0.11
     zákaz
    0.10
     müşter
    0.09
     ग्राह
    0.09
     ग्राहक
    0.09
     клиент
    0.09
     bedienen
    0.09
     प्रतिक्रिया
    0.08
     പ്രതിക
    0.08
     klanten
    0.08
    Act Density 0.032%

    No Known Activations