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

    Neuronpedia

    INDEX
    Explanations

    questions directed at you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +
    0.43
     scenes
    0.43
     eine
    0.39
     uses
    0.38
    ],
    0.38
     initialized
    0.38
    ly
    0.38
     range
    0.38
     equivalents
    0.38
     stej
    0.38
    POSITIVE LOGITS
     ನಮ್ಮ
    0.59
     OUR
    0.58
     خود
    0.57
     mình
    0.56
     our
    0.54
     देम
    0.54
     우리
    0.53
     그녀
    0.53
     আমাদের
    0.52
     theirs
    0.52
    Act Density 0.050%

    No Known Activations