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

    Neuronpedia

    INDEX
    Explanations

    Scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    优质的
    -0.07
    输送
    -0.07
     euth
    -0.07
     Comple
    -0.07
    牒
    -0.07
    =find
    -0.07
     لدى
    -0.07
    .Trans
    -0.07
    tığı
    -0.07
    _SYN
    -0.07
    POSITIVE LOGITS
    Ta
    0.07
    漲
    0.07
    帝国
    0.07
    zel
    0.07
     Tao
    0.07
    ränk
    0.07
     Departments
    0.07
    ->
    0.07
    اهل
    0.07
    槚
    0.07
    Act Density 0.009%

    No Known Activations