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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by px

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     മൃ
    0.58
    क्स
    0.52
    仁
    0.52
     Multimedia
    0.51
     ডেপুটি
    0.50
    ক্ক
    0.49
    𒂠
    0.48
    毫米
    0.47
    秾
    0.47
    incipal
    0.47
    POSITIVE LOGITS
     vậy
    0.46
    '
    0.44
    ahuje
    0.42
    podob
    0.41
    or
    0.41
    !")
    0.40
    arach
    0.39
     \}
    0.39
    션을
    0.39
    arai
    0.39
    Act Density 0.000%

    No Known Activations