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

    Neuronpedia

    INDEX
    Explanations

    Mi prefix words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distinct
    0.99
     merits
    0.89
     모양
    0.84
     mythical
    0.82
    moral
    0.82
    ục
    0.81
    wendung
    0.80
    mbox
    0.79
     комитета
    0.78
     minimize
    0.78
    POSITIVE LOGITS
    ubishi
    1.49
    IMUM
    1.35
    HAEL
    1.34
    arbeiter
    1.32
    rzost
    1.30
    芾
    1.30
    ędzynarod
    1.30
    饯
    1.28
    hael
    1.27
    nesota
    1.27
    Act Density 0.384%

    No Known Activations