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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bearings
    -0.07
    reat
    -0.06
    を持
    -0.06
    ;++
    -0.06
     devastation
    -0.06
     것입니다
    -0.06
    الی
    -0.06
    mc
    -0.06
     gasoline
    -0.06
    ency
    -0.06
    POSITIVE LOGITS
     involvement
    0.06
     PROGRAM
    0.06
    _extra
    0.06
     DRIVER
    0.06
    nutrition
    0.06
    Roboto
    0.06
     움
    0.06
     ضد
    0.06
     zase
    0.06
     COLLECTION
    0.06
    Act Density 0.084%

    No Known Activations