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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    言えば
    -0.47
     ardından
    -0.43
     विश्वसनीयता
    -0.43
     a
    -0.42
     accommodate
    -0.41
     those
    -0.40
    olerance
    -0.40
     an
    -0.40
     it
    -0.39
     refiri
    -0.39
    POSITIVE LOGITS
    is
    0.88
    has
    0.74
    ंदीखरीदारी
    0.72
     חיצוניים
    0.71
     يتيمه
    0.69
    Personendaten
    0.69
    ismet
    0.68
    MLLoader
    0.68
    sizeCache
    0.67
     isa
    0.65
    Act Density 0.001%

    No Known Activations