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

    Neuronpedia

    INDEX
    Explanations

    technical and patent language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    </h4>
    -0.77
     (
    -0.73
     (€
    -0.71
     themſelves
    -0.66
    （
    -0.65
     （
    -0.63
     (#
    -0.63
     (£
    -0.62
     NDEBUG
    -0.61
     (‘
    -0.60
    POSITIVE LOGITS
    )))),
    1.50
    )</
    1.48
    )),
    1.44
    )}}
    1.43
    ),
    1.41
    ))),
    1.41
    )})
    1.41
    '),
    1.41
    )
    1.41
    .)
    1.40
    Act Density 1.329%

    No Known Activations