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

    Neuronpedia

    INDEX
    Explanations

    pipeline What

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dynamo
    0.46
     જોઈ
    0.40
     interes
    0.38
    完
    0.38
     YouTube
    0.38
     Team
    0.38
     звук
    0.37
    ሮ
    0.37
     Youtube
    0.36
     Tiktok
    0.36
    POSITIVE LOGITS
    isAssignableFrom
    0.42
    ossing
    0.41
    袅
    0.40
    திகளை
    0.39
    முகச்
    0.39
    kých
    0.38
    企業の
    0.38
     ওয়াস
    0.38
    gesellschaft
    0.38
    acula
    0.38
    Act Density 0.001%

    No Known Activations