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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rovněž
    -0.06
     Triangle
    -0.06
     brings
    -0.06
     FormGroup
    -0.06
     فاصله
    -0.06
     jen
    -0.05
    claimed
    -0.05
    .MoveNext
    -0.05
     merkez
    -0.05
    Mo
    -0.05
    POSITIVE LOGITS
    ód
    0.08
    ر
    0.07
    орд
    0.07
    _testing
    0.06
    .FloatTensor
    0.06
    Inverse
    0.06
    iese
    0.06
    atchewan
    0.06
    atin
    0.06
     padr
    0.06
    Act Density 0.000%

    No Known Activations