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

    Neuronpedia

    INDEX
    Explanations

    Nav

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Livingston
    -0.08
    ีฬ
    -0.07
     Protestant
    -0.07
    .sn
    -0.07
    116
    -0.06
     článek
    -0.06
     Island
    -0.06
    からの
    -0.06
     Child
    -0.06
    変わ
    -0.06
    POSITIVE LOGITS
     PO
    0.06
    评价
    0.06
    _TIMES
    0.06
     号
    0.06
    udden
    0.06
     негатив
    0.06
     lékař
    0.06
     DIE
    0.06
    خدام
    0.06
    <bool
    0.06
    Act Density 0.005%

    No Known Activations