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

    Neuronpedia

    INDEX
    Explanations

    avoiding spoilers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -प
    -0.07
     mommy
    -0.07
    �
    -0.06
     siege
    -0.06
    Filed
    -0.06
     azalt
    -0.06
    .split
    -0.06
    ertia
    -0.06
     completionHandler
    -0.06
    یزات
    -0.06
    POSITIVE LOGITS
    radient
    0.07
    207
    0.07
     답
    0.06
    uem
    0.06
    _DECLARE
    0.06
    Few
    0.06
    ем
    0.06
    크
    0.06
    पन
    0.06
     intestinal
    0.06
    Act Density 0.059%

    No Known Activations