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

    Neuronpedia

    INDEX
    Explanations

    lengths, friends, and buying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ｺ
    0.38
    终止
    0.36
     هیچ
    0.34
     plume
    0.34
     Pourtant
    0.34
     пишет
    0.34
     nevertheless
    0.34
     hiatus
    0.33
     ያለ
    0.33
    Termination
    0.33
    POSITIVE LOGITS
    your
    0.41
    owned
    0.41
    serving
    0.40
    saves
    0.40
     చేయడానికి
    0.39
    ở
    0.39
    hese
    0.39
    INIS
    0.38
     পরিশোধ
    0.38
    嚀
    0.38
    Act Density 0.005%

    No Known Activations