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

    Neuronpedia

    INDEX
    Explanations

    .subplot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (scan
    -0.06
     поход
    -0.06
     steadily
    -0.06
     fraction
    -0.06
     minValue
    -0.06
     anth
    -0.06
     Decoration
    -0.06
    _By
    -0.06
     thresholds
    -0.06
     Fs
    -0.06
    POSITIVE LOGITS
     YYYY
    0.07
     chart
    0.07
    يلي
    0.07
    sur
    0.07
     Lama
    0.06
    ım
    0.06
     Initialize
    0.06
    ubbo
    0.06
    혹
    0.06
     näch
    0.06
    Act Density 0.001%

    No Known Activations