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

    Neuronpedia

    INDEX
    Explanations

    Chinese characters and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zs
    -0.08
    �
    -0.08
    es
    -0.07
    cwd
    -0.07
    志愿服务
    -0.07
     pursue
    -0.07
    .EventQueue
    -0.07
    .getExternal
    -0.07
    г
    -0.07
    (itr
    -0.07
    POSITIVE LOGITS
    クリック
    0.07
     línea
    0.07
    一
    0.06
     topped
    0.06
     类
    0.06
     mixin
    0.06
    𫓹
    0.06
     liner
    0.06
    .bottom
    0.06
     trim
    0.06
    Act Density 0.058%

    No Known Activations