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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    انا
    -0.07
    testdata
    -0.07
     nuru
    -0.07
     подход
    -0.07
     Lords
    -0.07
    饭
    -0.07
     Tests
    -0.07
    .track
    -0.07
    .words
    -0.07
    หม
    -0.06
    POSITIVE LOGITS
     qued
    0.07
    _passwd
    0.06
     ​
    0.06
     Oct
    0.06
    ñana
    0.06
     dinosaur
    0.06
    Thunder
    0.06
     Geh
    0.06
    fname
    0.06
    技
    0.06
    Act Density 0.023%

    No Known Activations