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

    Neuronpedia

    INDEX
    Explanations

    both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     właśnie
    0.29
     आशंका
    0.29
     लड़की
    0.28
    거든요
    0.27
     desaparecer
    0.26
    <unused429>
    0.26
    🩺
    0.26
     appunto
    0.25
    )【
    0.25
    )‏
    0.25
    POSITIVE LOGITS
     both
    0.40
    both
    0.36
    Both
    0.36
     både
    0.33
    ทั้ง
    0.32
     Both
    0.31
     zowel
    0.29
    b
    0.28
    Co
    0.28
     entrambi
    0.27
    Act Density 0.504%

    No Known Activations