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

    Neuronpedia

    INDEX
    Explanations

    assign an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .=
    0.44
    nicki
    0.40
    روف
    0.38
    най
    0.37
    ನದ
    0.37
     государство
    0.37
    пы
    0.37
    nati
    0.37
     небо
    0.36
     supon
    0.36
    POSITIVE LOGITS
     также
    0.43
    했고
    0.43
     також
    0.42
    outgoing
    0.42
     recipient
    0.41
    膛
    0.41
     publik
    0.40
    Outgoing
    0.40
     captures
    0.38
     Publication
    0.38
    Act Density 0.002%

    No Known Activations