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

    Neuronpedia

    INDEX
    Explanations

    causing actions or effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.55
     relies
    0.44
    name
    0.44
    oi
    0.43
     percep
    0.41
    fly
    0.41
     with
    0.40
     becomes
    0.39
     undergoing
    0.39
    differ
    0.39
    POSITIVE LOGITS
     باعث
    0.84
     menyebabkan
    0.77
    導致
    0.66
    ทำให้
    0.64
     khiến
    0.63
     কেড়ে
    0.62
    导致
    0.61
     causing
    0.60
     mendorong
    0.58
     ทำให้
    0.57
    Act Density 0.163%

    No Known Activations