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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .yang
    -0.07
    らず
    -0.07
    =\'
    -0.06
    -light
    -0.06
    Ra
    -0.06
     Mazda
    -0.06
    ด
    -0.06
    .threshold
    -0.06
     вз
    -0.06
    roud
    -0.06
    POSITIVE LOGITS
     replaced
    0.07
    ouncement
    0.07
    记
    0.07
     hide
    0.07
     cameo
    0.07
    /full
    0.06
     benchmark
    0.06
     hunt
    0.06
     että
    0.06
    (view
    0.06
    Act Density 0.000%

    No Known Activations