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

    Neuronpedia

    INDEX
    Explanations

    3, 4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Automated
    -0.08
    334
    -0.07
    خت
    -0.07
    ystem
    -0.06
    cover
    -0.06
    -non
    -0.06
     consider
    -0.06
    throw
    -0.06
    guarded
    -0.06
    เภ
    -0.06
    POSITIVE LOGITS
    =http
    0.07
    >>,↵
    0.07
    .setVerticalGroup
    0.07
     fitte
    0.06
        
    0.06
    .HORIZONTAL
    0.06
    (IOException
    0.06
    .attack
    0.06
    Сп
    0.06
    —even
    0.06
    Act Density 0.030%

    No Known Activations