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

    Neuronpedia

    INDEX
    Explanations

    accented vowels or diacritics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ic
    0.62
    ed
    0.61
    en
    0.61
    u
    0.59
     M
    0.59
     G
    0.58
    ção
    0.57
     l
    0.56
    et
    0.55
     New
    0.55
    POSITIVE LOGITS
     Фурга
    0.63
    calup
    0.60
    DCTask
    0.58
     аккумуля
    0.55
    ם
    0.55
    zovaniyu
    0.54
    큥
    0.54
    ра
    0.54
     exorbit
    0.54
     adhipp
    0.54
    Act Density 0.016%

    No Known Activations