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

    Neuronpedia

    INDEX
    Explanations

    letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ڰ
    -0.07
    팻
    -0.07
     trà
    -0.07
    _pll
    -0.07
    互联
    -0.07
    BTTag
    -0.07
    箧
    -0.07
    Writable
    -0.07
     pll
    -0.06
    //[
    -0.06
    POSITIVE LOGITS
    执法
    0.08
    人的
    0.07
    先生
    0.07
    eguard
    0.07
    (expected
    0.06
    蚁
    0.06
    .U
    0.06
    冠军
    0.06
    剧组
    0.06
     funding
    0.06
    Act Density 0.012%

    No Known Activations