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

    Neuronpedia

    INDEX
    Explanations

    tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৃঙ্খলা
    0.56
    氇
    0.50
     و
    0.49
    中でも
    0.49
    \/}
    0.49
     त
    0.48
     चि
    0.48
    ಿದರೆ
    0.47
     dukkham
    0.47
    OR
    0.46
    POSITIVE LOGITS
    The
    0.77
    ın
    0.74
     informó
    0.66
    6
    0.66
    са
    0.63
    8
    0.63
    ے
    0.63
    <0xDF>
    0.62
    </h3>
    0.61
    9
    0.59
    Act Density 0.036%

    No Known Activations