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

    Neuronpedia

    INDEX
    Explanations

    Golden Sands, Pick to Left, Intranet, Hour Coffee

    np_acts-logits-general · gemini-2.5-flash-lite

    API key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     עם
    0.59
    第一個
    0.58
    aabb
    0.58
     ،
    0.57
    yya
    0.57
    ,((
    0.55
    翀
    0.55
    ارك
    0.54
     idxf
    0.54
     چون
    0.53
    POSITIVE LOGITS
     will
    0.90
     can
    0.85
    ↵
    0.81
     are
    0.79
    5
    0.78
     and
    0.74
    and
    0.74
     će
    0.69
    ۵
    0.69
    ud
    0.65
    Act Density 6.279%

    No Known Activations