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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mankind
    -0.07
    handling
    -0.07
    	Rect
    -0.06
    ิทย
    -0.06
     Highland
    -0.06
    ующие
    -0.06
     nightly
    -0.06
    зь
    -0.06
    [ch
    -0.06
     forcing
    -0.06
    POSITIVE LOGITS
    cron
    0.08
    .python
    0.07
     aftermath
    0.06
     ARGS
    0.06
     contag
    0.06
     Cont
    0.06
    ']:
    0.06
    (cur
    0.06
     Ini
    0.06
    duğu
    0.06
    Act Density 0.014%

    No Known Activations