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

    Neuronpedia

    INDEX
    Explanations

    windows 10 and 11

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    0.68
    т
    0.63
    י
    0.57
     up
    0.54
    ar
    0.54
    ten
    0.51
     aus
    0.51
    ี
    0.51
    ا
    0.50
    ıya
    0.50
    POSITIVE LOGITS
    ología
    0.57
     Chameleon
    0.56
    <unused2199>
    0.55
     Até
    0.55
     wandered
    0.54
     Ephesus
    0.54
     İyi
    0.54
     prakt
    0.54
     Motto
    0.54
     праздник
    0.53
    Act Density 0.002%

    No Known Activations