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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gap
    -0.07
     đây
    -0.06
    llx
    -0.06
    SV
    -0.06
     Shi
    -0.06
     Kremlin
    -0.06
    Dam
    -0.06
    pager
    -0.06
    νώ
    -0.06
    Phone
    -0.06
    POSITIVE LOGITS
    _unc
    0.06
    emme
    0.06
    ="./
    0.06
     única
    0.06
    특별시
    0.06
    lobal
    0.06
    ?><
    0.06
     **)
    0.06
    orarily
    0.06
    prevState
    0.06
    Act Density 0.015%

    No Known Activations