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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.88
    :
    0.76
     a
    0.73
     January
    0.67
     Exposition
    0.67
     an
    0.65
     his
    0.64
     Tetrahedron
    0.63
     Página
    0.63
     pensamientos
    0.60
    POSITIVE LOGITS
     or
    1.02
    หรือ
    1.02
     voire
    1.00
     или
    0.98
     혹은
    0.97
     hoặc
    0.95
     அல்லது
    0.90
     কিংবা
    0.88
    もしくは
    0.87
     atau
    0.87
    Act Density 0.008%

    No Known Activations