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

    Neuronpedia

    INDEX
    Explanations

    character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <h
    -0.08
     utf
    -0.08
    责任
    -0.07
    尤
    -0.07
     Yun
    -0.07
    HY
    -0.07
     justification
    -0.07
     Subtract
    -0.07
    _define
    -0.07
    激励
    -0.07
    POSITIVE LOGITS
    阀门
    0.07
     Wroc
    0.07
    ଓ
    0.07
     محافظ
    0.07
    ��
    0.07
    רעי
    0.07
    考上
    0.07
     ())
    0.07
    .pag
    0.06
    𫫇
    0.06
    Act Density 0.007%

    No Known Activations