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

    Neuronpedia

    INDEX
    Explanations

    -nil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seems
    -0.07
     пу
    -0.07
    ΥΝ
    -0.07
    .assertAlmostEqual
    -0.06
     homosex
    -0.06
     menacing
    -0.06
     unimagin
    -0.06
     distracted
    -0.06
     bubb
    -0.06
     había
    -0.06
    POSITIVE LOGITS
    antics
    0.06
     acquisitions
    0.06
    ology
    0.06
     Held
    0.06
     Kahn
    0.06
    rored
    0.06
    ###############################################################################↵
    0.06
    ppt
    0.06
    اسي
    0.06
    etched
    0.06
    Act Density 0.001%

    No Known Activations