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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nebude
    -0.06
     bullied
    -0.06
     coward
    -0.06
     địch
    -0.06
     pasture
    -0.06
    allenge
    -0.06
     coraz
    -0.06
    GREE
    -0.06
    střed
    -0.06
    喊
    -0.06
    POSITIVE LOGITS
    реть
    0.07
    .ct
    0.07
     Bit
    0.07
    parameter
    0.06
    ulating
    0.06
     přech
    0.06
    چی
    0.06
    rat
    0.06
    ener
    0.06
    uate
    0.06
    Act Density 0.000%

    No Known Activations