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

    Neuronpedia

    INDEX
    Explanations

    Un

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ath
    -0.07
    推荐阅读
    -0.07
     coeff
    -0.07
     ומת
    -0.07
    呗
    -0.07
     Ж
    -0.07
    .web
    -0.07
     Ż
    -0.07
    超强
    -0.06
     snork
    -0.06
    POSITIVE LOGITS
     roman
    0.09
     (
    0.08
    成员
    0.08
    可靠
    0.08
    acers
    0.08
     lamin
    0.08
    姗
    0.07
     sequential
    0.07
    ,
    0.07
     placement
    0.07
    Act Density 0.052%

    No Known Activations