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

    Neuronpedia

    INDEX
    Explanations

    qualifiers and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     واست
    0.35
    ो
    0.33
    :“
    0.32
     που
    0.31
     it
    0.31
     Ло
    0.30
     to
    0.30
    ow
    0.30
    стро
    0.30
    ීමට
    0.30
    POSITIVE LOGITS
    ED
    0.32
    న్
    0.31
    X
    0.30
    ال
    0.30
    מ
    0.29
    ח
    0.29
    ne
    0.29
    تين
    0.28
     دانلود
    0.28
    𝐡
    0.28
    Act Density 0.889%

    No Known Activations