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

    Neuronpedia

    INDEX
    Explanations

    decentralized systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    तुरंग
    0.83
     потреб
    0.82
    textView
    0.79
    ور
    0.78
    ಧಾನ
    0.75
    lld
    0.75
     nouvel
    0.74
     sinned
    0.74
    из
    0.74
    η
    0.73
    POSITIVE LOGITS
    ו
    0.80
    itemize
    0.71
    ennzeichnet
    0.71
     зон
    0.69
    bees
    0.68
    ల
    0.68
    ত্র
    0.67
    ꒰
    0.67
     petty
    0.67
    にあった
    0.67
    Act Density 0.109%

    No Known Activations