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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unanim
    -0.07
    （
    -0.06
    ?>"><
    -0.06
    (Gravity
    -0.06
    .rd
    -0.06
    血
    -0.06
    Special
    -0.06
     性
    -0.06
    (Network
    -0.06
     acre
    -0.06
    POSITIVE LOGITS
    ;height
    0.06
     çık
    0.06
     Пост
    0.06
     padd
    0.06
     intervening
    0.06
     pedest
    0.06
    /source
    0.06
     cyclists
    0.06
     belle
    0.06
    /pdf
    0.06
    Act Density 0.027%

    No Known Activations