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

    Neuronpedia

    INDEX
    Explanations

    code related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أمام
    -0.07
    積極
    -0.07
    퍠
    -0.06
    ondo
    -0.06
     Sno
    -0.06
    ended
    -0.06
     denial
    -0.06
    옭
    -0.06
    iates
    -0.06
    ﰿ
    -0.06
    POSITIVE LOGITS
    .Proxy
    0.08
    𝑤
    0.07
    현
    0.07
     membr
    0.07
    .he
    0.07
    DSP
    0.07
    个人信息
    0.07
    graphql
    0.07
    �
    0.07
     dbl
    0.07
    Act Density 0.016%

    No Known Activations