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

    Neuronpedia

    INDEX
    Explanations

    command line arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فِي
    0.37
    දු
    0.37
    !”,
    0.37
    !’
    0.36
     حدیث
    0.36
    LOW
    0.36
     계산
    0.35
    窮
    0.35
    dom
    0.35
     подроб
    0.35
    POSITIVE LOGITS
     Above
    0.46
     हमने
    0.43
     Uses
    0.41
     above
    0.40
     Access
    0.40
     `<
    0.39
     noqa
    0.39
     ABV
    0.39
     "<
    0.39
     первая
    0.39
    Act Density 0.000%

    No Known Activations