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

    Neuronpedia

    INDEX
    Explanations

    incorrect function arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    校外
    -0.07
    まれ
    -0.07
    מל
    -0.07
    MISSION
    -0.06
    .Sort
    -0.06
    .pic
    -0.06
    LoginPage
    -0.06
    letion
    -0.06
     Solic
    -0.06
    ቨ
    -0.06
    POSITIVE LOGITS
     الشمال
    0.08
    כאב
    0.08
    EC
    0.07
     marches
    0.07
    鲪
    0.07
     שעות
    0.07
    蜜蜂
    0.07
    (cb
    0.07
     scraped
    0.07
     сын
    0.07
    Act Density 0.022%

    No Known Activations