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

    Neuronpedia

    INDEX
    Explanations

    programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lara
    0.72
     English
    0.70
     Bluest
    0.66
    驼
    0.65
    FactoryBean
    0.64
     distance
    0.64
    English
    0.63
    옥
    0.63
    蜈
    0.62
     Gunn
    0.61
    POSITIVE LOGITS
     Sebastián
    0.82
     Shea
    0.82
     Sebastian
    0.82
     Cell
    0.81
    Save
    0.81
    Cell
    0.80
     CELL
    0.80
     Marin
    0.80
     NSE
    0.80
     Marcy
    0.79
    Act Density 1.124%

    No Known Activations