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

    Neuronpedia

    INDEX
    Explanations

    number and digit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     winners
    -0.07
     lawsuit
    -0.07
    大宗
    -0.07
    찮
    -0.07
    没有什么
    -0.07
    怀念
    -0.07
    compile
    -0.07
    抒
    -0.07
     thing
    -0.07
     输
    -0.07
    POSITIVE LOGITS
    .segment
    0.07
     достат
    0.07
     AR
    0.07
    jaw
    0.07
    кова
    0.06
    SMART
    0.06
     AUT
    0.06
     мягк
    0.06
    롓
    0.06
    elo
    0.06
    Act Density 0.012%

    No Known Activations