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

    Neuronpedia

    INDEX
    Explanations

    express request handlers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ({\
    0.97
    thane
    0.86
     Affordable
    0.81
    abilit
    0.80
     ([
    0.80
     उत्तराखण्ड
    0.78
     quam
    0.77
     بارے
    0.77
    0.76
     আত্মার
    0.76
    POSITIVE LOGITS
     boom
    0.79
     Slow
    0.71
     ř
    0.71
     slow
    0.70
     부
    0.68
     跟
    0.67
     Tens
    0.67
     plötzlich
    0.67
    ू
    0.66
     Schu
    0.66
    Act Density 0.001%

    No Known Activations