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

    Neuronpedia

    INDEX
    Explanations

    Background of the Invention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    markdown
    0.61
     குறித்து
    0.61
    during
    0.61
    everything
    0.61
     ಅದರ
    0.60
    について
    0.60
     над
    0.59
    rägt
    0.57
    超过
    0.57
    specific
    0.57
    POSITIVE LOGITS
     present
    2.12
     Present
    1.78
    Present
    1.70
     presente
    1.64
     présent
    1.59
    present
    1.53
     presenti
    1.52
     présente
    1.51
     presentes
    1.47
     PRESENT
    1.33
    Act Density 0.001%

    No Known Activations