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

    Neuronpedia

    INDEX
    Explanations

    experience level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rating
    0.80
     Therm
    0.73
     Literatura
    0.71
     Photographer
    0.69
     Ratings
    0.69
     Με
    0.68
     Improve
    0.68
     Model
    0.66
     Все
    0.66
     картина
    0.65
    POSITIVE LOGITS
    ossal
    0.86
     virt
    0.80
    xas
    0.80
    esseur
    0.79
    笏
    0.78
    oken
    0.77
    gtrsim
    0.76
     maestros
    0.74
    asso
    0.73
    🫤
    0.73
    Act Density 0.002%

    No Known Activations