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

    Neuronpedia

    INDEX
    Explanations

    forum/chat text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     объек
    -0.06
     часом
    -0.06
     bour
    -0.06
    .assertRaises
    -0.06
    отор
    -0.06
     thriller
    -0.06
     mingle
    -0.06
     الخاص
    -0.05
     шир
    -0.05
     Vapor
    -0.05
    POSITIVE LOGITS
    human
    0.09
    Snake
    0.07
     checkbox
    0.07
    Chef
    0.07
     randomly
    0.07
    enth
    0.07
    OMATIC
    0.07
    -package
    0.07
    ivant
    0.07
     consciously
    0.07
    Act Density 0.021%

    No Known Activations