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

    Neuronpedia

    INDEX
    Explanations

    engineering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spike
    -0.07
     inlet
    -0.06
     Sudoku
    -0.06
     wz
    -0.06
     Booth
    -0.06
    baru
    -0.06
     rant
    -0.06
    ضة
    -0.06
    _OUT
    -0.06
    _Read
    -0.06
    POSITIVE LOGITS
    ・・・↵↵
    0.07
     gerekir
    0.07
    على
    0.07
    еля
    0.07
     undermine
    0.06
     pesquisa
    0.06
     engineered
    0.06
    (isset
    0.06
    .groupby
    0.06
     الاح
    0.06
    Act Density 0.002%

    No Known Activations