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

    Neuronpedia

    INDEX
    Explanations

    bits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diferenças
    0.40
     Lus
    0.39
     asemenea
    0.38
    flush
    0.37
    drawable
    0.36
     yana
    0.36
    കളെ
    0.36
    $[\
    0.36
    Lus
    0.36
     det
    0.35
    POSITIVE LOGITS
    CriteriaUtils
    0.44
     wrap
    0.39
     wrapping
    0.38
    perluan
    0.38
     ສະ
    0.38
     सिल
    0.37
     Wrap
    0.37
    ኩ
    0.37
    鋳
    0.36
     חיצוני
    0.36
    Act Density 0.000%

    No Known Activations