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

    Neuronpedia

    INDEX
    Explanations

    for you or all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marinated
    0.82
     james
    0.80
    james
    0.78
     Psychological
    0.78
     JAMES
    0.78
    James
    0.75
    ámenes
    0.75
    ('./
    0.75
     ridges
    0.75
    Myers
    0.74
    POSITIVE LOGITS
     पप्पू
    0.76
     ecology
    0.75
     ele
    0.75
     happy
    0.73
     Happy
    0.70
     anthropology
    0.69
     অধিকারী
    0.69
     entity
    0.68
     Manny
    0.67
    ဘူး
    0.67
    Act Density 0.065%

    No Known Activations