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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.79
    欢迎
    0.68
     emp
    0.65
    닷
    0.65
    の
    0.63
     pads
    0.61
     forever
    0.61
    ικό
    0.60
    emuan
    0.60
    的
    0.60
    POSITIVE LOGITS
    soluble
    0.72
    Wey
    0.69
     स्टाइलिश
    0.67
     siguiente
    0.66
     الاثنين
    0.64
     sépt
    0.63
    딛
    0.62
    看不
    0.62
    ependant
    0.62
    existe
    0.62
    Act Density 0.116%

    No Known Activations