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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rxjs
    -0.07
    상품
    -0.07
    ")},↵
    -0.06
    ัตว
    -0.06
    문화
    -0.06
    .EditorButton
    -0.06
    لس
    -0.06
    خب
    -0.06
    ців
    -0.06
     trận
    -0.06
    POSITIVE LOGITS
     devote
    0.07
    (...
    0.06
     severe
    0.06
     torn
    0.06
     volatile
    0.06
     Veg
    0.06
     Weber
    0.06
     Bl
    0.06
     avenue
    0.06
     vortex
    0.06
    Act Density 0.000%

    No Known Activations