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

    Neuronpedia

    INDEX
    Explanations

    seeing your ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efter
    1.53
    ש
    1.50
    ःख
    1.38
    𝚜
    1.36
     Daarnaast
    1.35
     годов
    1.34
    на
    1.33
    и
    1.29
    ━
    1.27
    𝚗
    1.27
    POSITIVE LOGITS
     xét
    1.87
    了一眼
    1.46
    रेख
    1.35
    et
    1.32
     देखते
    1.31
    一眼
    1.30
    ジュアル
    1.28
    HasStarred
    1.27
     afectada
    1.23
    PropTypes
    1.22
    Act Density 0.174%

    No Known Activations