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

    Neuronpedia

    INDEX
    Explanations

    descriptions of specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     или
    0.77
     alebo
    0.77
     vagy
    0.73
     etc
    0.70
    等の
    0.70
     või
    0.70
     nebo
    0.65
     அல்லது
    0.64
     किंवा
    0.63
    、
    0.63
    POSITIVE LOGITS
    ოდა
    0.58
    磪
    0.56
     Tetra
    0.55
    केंसी
    0.55
    ूठी
    0.55
     generalized
    0.54
    ड़का
    0.54
     Notably
    0.54
    Тер
    0.54
    ሠ
    0.54
    Act Density 0.523%

    No Known Activations