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

    Neuronpedia

    INDEX
    Explanations

    np

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ‘’
    0.82
     Interestingly
    0.80
     असलेल्या
    0.80
    વણી
    0.79
     Afterward
    0.79
    áneamente
    0.79
     Significantly
    0.78
     (…)
    0.76
     üzere
    0.76
     Notably
    0.75
    POSITIVE LOGITS
    .
    2.31
    ./
    1.67
    ._
    1.62
    .//
    1.59
    .%
    1.55
    .?
    1.52
    .=
    1.49
    .`
    1.47
    .,
    1.43
    .):
    1.41
    Act Density 0.126%

    No Known Activations