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

    Neuronpedia

    INDEX
    Explanations

    objective meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    นิยม
    1.23
    ύ
    1.19
    icelli
    1.15
     euismod
    1.14
    sterdam
    1.14
    텍
    1.14
    тів
    1.11
    ্যাল
    1.08
    ের
    1.06
     koristiti
    1.06
    POSITIVE LOGITS
    सभी
    1.47
     esteemed
    1.44
     Darryl
    1.39
    ו
    1.38
     whereabouts
    1.35
    ança
    1.34
     touted
    1.33
    ganos
    1.32
     welds
    1.31
     únic
    1.30
    Act Density 0.000%

    No Known Activations