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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .k
    -0.07
    柴
    -0.06
    ��
    -0.06
     Pc
    -0.06
     nền
    -0.06
    _lvl
    -0.06
    -lg
    -0.06
     Corbyn
    -0.06
    άκ
    -0.06
     ترك
    -0.06
    POSITIVE LOGITS
    =========
    0.07
     tra
    0.07
    ------
    0.07
     wildlife
    0.07
     Enh
    0.06
     skeletons
    0.06
    -------
    0.06
     LENGTH
    0.06
    จร
    0.06
    .RESET
    0.06
    Act Density 0.042%

    No Known Activations