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

    Neuronpedia

    INDEX
    Explanations

    Coding, threading, Pricing, Lighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ically
    2.15
    ive
    1.96
    데
    1.79
    まあ
    1.79
    op
    1.79
     startling
    1.76
    ころ
    1.75
    Upcoming
    1.75
    orium
    1.73
     stunning
    1.71
    POSITIVE LOGITS
    ्ज
    2.76
    ilizce
    2.28
     वाला
    2.28
    ت
    2.17
    ला
    2.16
    ها
    2.16
    trong
    2.05
    턴
    2.04
    ו
    2.02
    towards
    2.02
    Act Density 0.752%

    No Known Activations