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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autre
    -1.54
     itself
    -1.46
     you
    -1.42
    懨
    -1.33
    を注文
    -1.27
     guitar
    -1.24
     disfraces
    -1.23
     bailando
    -1.20
     kami
    -1.18
     our
    -1.16
    POSITIVE LOGITS
     by
    1.77
    」。
    1.41
    ;");
    1.32
     from
    1.29
    」「
    1.28
     acolo
    1.27
     RNAs
    1.24
     Reprint
    1.20
    され
    1.20
    //!
    1.19
    Act Density 0.209%

    No Known Activations