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

    Neuronpedia

    INDEX
    Explanations

    funk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ма
    1.57
    ك
    1.34
    思います
    1.31
    ﻮ
    1.23
    ет
    1.22
    きました
    1.22
    ท
    1.22
    ﮯ
    1.20
    ン
    1.20
    н
    1.16
    POSITIVE LOGITS
    tól
    1.48
     palpitations
    1.45
     tempos
    1.41
    gladbach
    1.41
    بول
    1.40
    tive
    1.38
     pós
    1.38
     romp
    1.37
     plump
    1.34
    Sushi
    1.34
    Act Density 0.002%

    No Known Activations