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

    Neuronpedia

    INDEX
    Explanations

    HTML files/classes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .slide
    -0.08
     الأسهم
    -0.07
    leaflet
    -0.07
     servo
    -0.07
    ƣ
    -0.07
    篆
    -0.07
    铤
    -0.07
     whereas
    -0.07
    躬
    -0.07
    чреж
    -0.07
    POSITIVE LOGITS
    (\'
    0.08
    楊
    0.07
     hak
    0.07
    Two
    0.07
     convicted
    0.07
     irreversible
    0.07
    處理
    0.07
    谁能
    0.06
    CN
    0.06
    签名
    0.06
    Act Density 0.027%

    No Known Activations