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

    Neuronpedia

    INDEX
    Explanations

    describing states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    astr
    -0.07
     sạch
    -0.07
    게시
    -0.06
    Dans
    -0.06
    оло
    -0.06
    руч
    -0.06
    ็ค
    -0.06
    /service
    -0.06
     olası
    -0.06
    ابقات
    -0.06
    POSITIVE LOGITS
     updated
    0.06
     Wet
    0.06
     terror
    0.06
     meteor
    0.06
    :num
    0.06
     pued
    0.06
    を開
    0.06
     knights
    0.06
     pry
    0.06
     вий
    0.06
    Act Density 0.108%

    No Known Activations