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

    Neuronpedia

    INDEX
    Explanations

    re

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aira
    -0.08
     Cater
    -0.07
     XF
    -0.07
    _App
    -0.06
     LAND
    -0.06
     followers
    -0.06
     quantity
    -0.06
    -letter
    -0.06
    чики
    -0.06
     ช
    -0.06
    POSITIVE LOGITS
    (image
    0.06
    .TextImageRelation
    0.06
    (completion
    0.06
     affection
    0.06
     адрес
    0.06
    ！
    0.06
    LERİ
    0.06
    .CenterScreen
    0.06
     restless
    0.06
     wg
    0.06
    Act Density 0.000%

    No Known Activations