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

    Neuronpedia

    INDEX
    Explanations

    defined by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ціона
    0.57
    PrefabAsset
    0.50
     መጠቀም
    0.50
    ServiceImpl
    0.47
    㣙
    0.46
    降低
    0.45
    炡
    0.45
    𐱅
    0.45
    字幕
    0.45
     попере
    0.45
    POSITIVE LOGITS
    s
    0.66
    but
    0.57
     but
    0.57
     l
    0.54
    ess
    0.54
    c
    0.54
    j
    0.52
    o
    0.50
     pero
    0.49
    ld
    0.48
    Act Density 0.004%

    No Known Activations