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

    Neuronpedia

    INDEX
    Explanations

    pulsar stars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.94
    de
    0.85
     to
    0.80
    6
    0.77
    <
    0.73
     L
    0.72
    ية
    0.72
    to
    0.71
    ０
    0.71
    -\
    0.70
    POSITIVE LOGITS
     bạn
    0.70
     прибыли
    0.66
     investir
    0.64
    that
    0.64
     ними
    0.64
     други
    0.63
     организация
    0.63
     конферен
    0.63
     вами
    0.62
    ここ
    0.62
    Act Density 0.001%

    No Known Activations