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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.77
    styleType
    -0.71
    DrawerToggle
    -0.69
    ########.
    -0.69
     ويكيپيديا
    -0.68
     Roskov
    -0.65
    expandindo
    -0.65
    BufferException
    -0.64
    PerformLayout
    -0.62
    ftagPool
    -0.60
    POSITIVE LOGITS
     
    0.51
     Gravity
    0.47
     How
    0.47
    襟
    0.47
     Sugar
    0.46
     re
    0.45
     Civil
    0.45
     thảo
    0.44
     discussion
    0.44
    Посилання
    0.44
    Act Density 0.006%

    No Known Activations