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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seizing
    -0.07
     offending
    -0.07
    驗
    -0.06
     Driving
    -0.06
     commander
    -0.06
     Hell
    -0.06
     backers
    -0.06
     speculated
    -0.06
    zet
    -0.06
     Governor
    -0.06
    POSITIVE LOGITS
    (EX
    0.07
     McCl
    0.07
    ілі
    0.06
    /gen
    0.06
     BAM
    0.06
    ์ได
    0.06
    #__
    0.06
    ayıf
    0.06
     впол
    0.06
    폰
    0.06
    Act Density 0.010%

    No Known Activations