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

    Neuronpedia

    INDEX
    Explanations

    healthline.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    चुनाव
    0.72
    de
    0.72
    "/
    0.69
    Madonna
    0.67
    "\
    0.63
    Trash
    0.62
    Си
    0.61
    dreams
    0.61
    "",
    0.60
     मिलाएं
    0.59
    POSITIVE LOGITS
     sep
    0.62
     scant
    0.61
     ovu
    0.60
     hundred
    0.59
    ш
    0.58
     takers
    0.58
     marketed
    0.57
    ០
    0.57
    ູ່
    0.57
     şekilde
    0.57
    Act Density 0.004%

    No Known Activations