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

    Neuronpedia

    INDEX
    Explanations

    number 42

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lẫn
    0.43
    ét
    0.41
    ELS
    0.40
    áln
    0.39
    Alc
    0.38
    गील
    0.38
    éli
    0.36
    oster
    0.35
    sembles
    0.35
    Dé
    0.35
    POSITIVE LOGITS
     skiprows
    0.56
     stdout
    0.54
     porque
    0.53
     alphanumeric
    0.53
     aveva
    0.53
     emoji
    0.52
     ஏனெனில்
    0.52
     onde
    0.52
     merah
    0.52
     angka
    0.52
    Act Density 0.016%

    No Known Activations