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

    Neuronpedia

    INDEX
    Explanations

    code comments and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amura
    0.42
    hee
    0.37
     danced
    0.37
    க்கா
    0.36
    ദം
    0.36
    螯
    0.35
    Norman
    0.35
     ایپلی
    0.34
     ব্যাক
    0.34
     modulated
    0.34
    POSITIVE LOGITS
     -(
    0.83
    //{
    0.76
    -(
    0.76
    //$
    0.75
    //}
    0.74
    }-(
    0.72
     //{
    0.71
     (!(
    0.70
     <!--<
    0.70
     //}
    0.68
    Act Density 0.008%

    No Known Activations