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

    Neuronpedia

    INDEX
    Explanations

    said followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    로
    0.62
    ৭
    0.53
    neux
    0.51
    intl
    0.50
    ৮
    0.49
    us
    0.49
    pflege
    0.49
    是因为
    0.48
    に
    0.48
    ਕ
    0.47
    POSITIVE LOGITS
    0.61
    ύν
    0.59
    യാണ്
    0.57
     oss
    0.55
     participe
    0.52
     ima
    0.52
    ς
    0.52
    0.49
    0.49
    ȱ
    0.49
    Act Density 0.011%

    No Known Activations