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

    Neuronpedia

    INDEX
    Explanations

    alternative or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     japanese
    0.39
     chamada
    0.38
     meisten
    0.37
     descobrir
    0.36
     hepat
    0.36
    Histoire
    0.36
     mutations
    0.36
    鴟
    0.35
    ɧ
    0.35
     ports
    0.34
    POSITIVE LOGITS
     또는
    0.62
     или
    0.61
     किंवा
    0.59
     அல்லது
    0.58
     অথবা
    0.57
    或其他
    0.55
     alebo
    0.55
     或者
    0.55
    ”,
    0.54
     veya
    0.52
    Act Density 0.228%

    No Known Activations