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

    Neuronpedia

    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XObject
    -0.07
     predictor
    -0.06
     Programmer
    -0.06
    ................
    -0.06
    -----------
    -0.06
     ----------------------------------------------------------------------↵
    -0.06
    .Interop
    -0.06
    ragon
    -0.06
    Margins
    -0.06
     workflow
    -0.06
    POSITIVE LOGITS
     sober
    0.10
     solemn
    0.09
     astronomy
    0.08
     lumin
    0.07
    لط
    0.07
    .assertAlmostEqual
    0.07
     ominous
    0.06
     공식
    0.06
     jpeg
    0.06
     Gore
    0.06
    Act Density 0.002%

    No Known Activations