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

    Neuronpedia

    INDEX
    Explanations

    ranges of numbers and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    கொ
    0.41
    Ꮑ
    0.41
    ຮ
    0.39
     سپورټ
    0.37
    い
    0.35
     odpowied
    0.35
    એ
    0.35
    {|
    0.34
     ഒന്ന
    0.34
     Аб
    0.34
    POSITIVE LOGITS
     Mills
    0.38
    Ville
    0.37
     మాట్లాడు
    0.37
     immobilier
    0.37
    עד
    0.36
     fumes
    0.36
    رفته
    0.35
     చెబు
    0.35
    immobil
    0.35
    erty
    0.34
    Act Density 0.000%

    No Known Activations