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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #,
    0.75
    ).[
    0.74
    #:
    0.74
     elif
    0.72
    )#
    0.71
    ,#
    0.71
    #.
    0.70
    elif
    0.70
    +#
    0.70
    #
    0.69
    POSITIVE LOGITS
     //
    2.68
    //
    1.90
     //'
    1.70
     ///
    1.68
     //-
    1.68
     //.
    1.66
     //<
    1.54
     ////
    1.53
     //[
    1.51
    ///
    1.49
    Act Density 0.389%

    No Known Activations