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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     насељу
    -0.99
     للمعارف
    -0.98
    StoryboardSegue
    -0.94
    MigrationBuilder
    -0.93
    findpost
    -0.92
     Efq
    -0.90
    MemoryWarning
    -0.88
     '\\;'
    -0.86
     الرياضيه
    -0.84
    verwijspagina
    -0.84
    POSITIVE LOGITS
    s
    0.70
    spo
    0.51
    sl
    0.51
    sg
    0.50
    ii
    0.49
    sd
    0.48
    ↵↵
    0.48
     
    0.46
    sc
    0.45
    *
    0.44
    Act Density 0.021%

    No Known Activations