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

    Neuronpedia

    INDEX
    Explanations

    is followed by a description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).]
    0.38
     रहीं
    0.36
    "/>.
    0.36
     ذریع
    0.35
    )।
    0.34
     आईं
    0.34
     গুণে
    0.34
    )?,
    0.33
     ہوں۔
    0.33
     거고
    0.33
    POSITIVE LOGITS
     has
    0.76
     goes
    0.73
     is
    0.71
     does
    0.71
     constitutes
    0.67
    has
    0.64
     creates
    0.64
     carries
    0.63
     differs
    0.63
     speaks
    0.62
    Act Density 0.194%

    No Known Activations