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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FIRST
    -0.06
    ‌د
    -0.06
    ιδ
    -0.06
    ('{{
    -0.06
    经验
    -0.06
    š
    -0.06
    ुभव
    -0.06
    eg
    -0.06
    xdc
    -0.06
    фектив
    -0.06
    POSITIVE LOGITS
    Strike
    0.07
     друж
    0.07
     athletes
    0.07
     Adult
    0.06
     gent
    0.06
    лена
    0.06
    790
    0.06
    .Real
    0.06
    <this
    0.06
     Rehabilitation
    0.06
    Act Density 0.002%

    No Known Activations