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

    Neuronpedia

    INDEX
    Explanations

    css selectors and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purification
    0.65
     Hepatitis
    0.64
     obtained
    0.64
     انجام
    0.63
     Obtain
    0.63
     eigen
    0.62
     Atkins
    0.62
     नव्हते
    0.62
     Boltzmann
    0.62
     Purification
    0.62
    POSITIVE LOGITS
     `#
    0.88
     `.
    0.87
    /*
    0.86
    (".
    0.84
    krit
    0.83
    #
    0.83
    るとき
    0.81
    ","#
    0.80
    @
    0.80
     `@
    0.80
    Act Density 0.089%

    No Known Activations