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
     sản
    -0.07
    Inicio
    -0.07
     ком
    -0.06
     unittest
    -0.06
     ethnic
    -0.06
    ेस
    -0.06
     incapac
    -0.06
     ره
    -0.06
    ناء
    -0.06
    >m
    -0.06
    POSITIVE LOGITS
    になり
    0.08
     shy
    0.07
    layer
    0.07
     μας
    0.07
     SHORT
    0.06
     lightweight
    0.06
     tarihli
    0.06
    ]]);↵
    0.06
     목록
    0.06
     achievable
    0.06
    Act Density 0.001%

    No Known Activations