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

    Neuronpedia

    INDEX
    Explanations

    prime factors, divisions, and points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ::
    0.64
    ("")
    0.63
    by
    0.62
    వంత
    0.60
    并
    0.60
    esterday
    0.59
    finding
    0.59
    something
    0.59
    rewrite
    0.59
     =
    0.58
    POSITIVE LOGITS
     jotka
    1.02
     ktoré
    0.88
     koje
    0.83
     które
    0.82
     които
    0.82
     које
    0.81
     которые
    0.80
     რომლებიც
    0.78
     që
    0.77
     které
    0.76
    Act Density 0.001%

    No Known Activations