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

    Neuronpedia

    INDEX
    Explanations

    near, closest, and margin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atern
    0.45
    מי
    0.44
    ⿱
    0.44
     정보를
    0.43
     지정
    0.42
    김
    0.42
    ligen
    0.41
     전부
    0.41
    ায়ন
    0.41
    agan
    0.39
    POSITIVE LOGITS
    ៦
    0.55
    Jpeg
    0.50
    stricken
    0.49
     مشتقه
    0.48
    льное
    0.48
     மாசு
    0.48
     neodymium
    0.48
    нное
    0.47
    нде
    0.46
    suppliers
    0.46
    Act Density 0.000%

    No Known Activations