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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PED
    -0.07
     MatSnackBar
    -0.06
    为什么
    -0.06
     naopak
    -0.06
    ESİ
    -0.06
    theros
    -0.06
     Colonel
    -0.06
    docs
    -0.06
     или
    -0.06
    Disp
    -0.05
    POSITIVE LOGITS
     roots
    0.07
    san
    0.07
     TC
    0.06
     pic
    0.06
     없었다
    0.06
    /out
    0.06
     British
    0.06
    ��
    0.06
     Renders
    0.06
    вищ
    0.06
    Act Density 0.084%

    No Known Activations