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

    Neuronpedia

    INDEX
    Explanations

    now that some point is dismissed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Somewhere
    0.49
    किसी
    0.45
     ถ้า
    0.42
    ถ้า
    0.42
    cuando
    0.40
    如果你
    0.40
     какой
    0.40
     ಯಾವುದ
    0.40
    这次
    0.39
     ơi
    0.39
    POSITIVE LOGITS
     ive
    0.52
     Ive
    0.50
     নিয়েছেন
    0.48
     telah
    0.47
     abbiamo
    0.46
     हमने
    0.46
     হয়েছেন
    0.46
     we
    0.44
     have
    0.44
     everyone
    0.44
    Act Density 0.003%

    No Known Activations