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

    Neuronpedia

    INDEX
    Explanations

    whole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мет
    -0.08
     bothered
    -0.07
     PST
    -0.07
    站
    -0.07
    _mex
    -0.06
    _pix
    -0.06
    Coding
    -0.06
    .gz
    -0.06
     英语
    -0.06
     iota
    -0.06
    POSITIVE LOGITS
     whole
    0.07
    (global
    0.06
    ��
    0.06
    (route
    0.06
     sach
    0.06
    위원회
    0.06
    (Global
    0.06
    งหมด
    0.06
     recursive
    0.06
     Elemental
    0.06
    Act Density 0.019%

    No Known Activations