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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肝
    -0.08
     inflammation
    -0.07
    흩
    -0.07
    �
    -0.07
    腹泻
    -0.07
    isValid
    -0.07
     Fill
    -0.06
    ー�
    -0.06
    they
    -0.06
     л
    -0.06
    POSITIVE LOGITS
    单价
    0.07
    歩いて
    0.06
    lse
    0.06
    跑到
    0.06
    交通大学
    0.06
    文學
    0.06
    ഴ
    0.06
    -rounded
    0.06
    ()['
    0.06
    חת
    0.06
    Act Density 0.007%

    No Known Activations