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

    Neuronpedia

    INDEX
    Explanations

    .R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     umb
    -0.07
     Stroke
    -0.07
     стран
    -0.06
    KN
    -0.06
     partitions
    -0.06
     Recording
    -0.06
     antic
    -0.06
     hatır
    -0.06
    .fun
    -0.06
    udd
    -0.06
    POSITIVE LOGITS
     vui
    0.07
    >)
    0.06
    人が
    0.06
     首页第
    0.06
    가요
    0.06
     böyle
    0.06
     prioritize
    0.06
     tüm
    0.06
     янва
    0.06
    '^$',
    0.06
    Act Density 0.002%

    No Known Activations