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

    Neuronpedia

    INDEX
    Explanations

    fatal outcomes and death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    阃
    0.49
    颀
    0.49
    文档
    0.48
     KAHN
    0.47
     УК
    0.46
    どのように
    0.45
    ن
    0.45
    フィン
    0.45
    腟
    0.45
     nouvel
    0.43
    POSITIVE LOGITS
    are
    0.48
    ut
    0.45
     سٹی
    0.44
    yh
    0.41
     City
    0.41
     slik
    0.40
    ICS
    0.40
     nii
    0.40
     bł
    0.40
    avid
    0.40
    Act Density 0.003%

    No Known Activations