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

    Neuronpedia

    INDEX
    Explanations

    break

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sắt
    -0.08
    اح
    -0.06
    ное
    -0.06
    ậ
    -0.06
    στά
    -0.06
     tad
    -0.06
    _ef
    -0.06
    컨
    -0.06
     reducers
    -0.06
    .Objects
    -0.06
    POSITIVE LOGITS
    _exam
    0.07
     تحميل
    0.06
     navig
    0.06
     Thank
    0.06
    STEM
    0.06
     Наз
    0.06
     horns
    0.06
     AMA
    0.06
    SZ
    0.06
    =no
    0.06
    Act Density 0.005%

    No Known Activations