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

    Neuronpedia

    INDEX
    Explanations

    deliver value/results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    সঙ্গে
    3.02
    ्स
    2.79
    𝔰
    2.79
    𝙨
    2.70
     Правда
    2.70
     इसमें
    2.68
    𝔱
    2.66
    𝔪
    2.63
     nuis
    2.62
    𝙢
    2.61
    POSITIVE LOGITS
    ра
    3.42
    ן
    2.92
    ল
    2.83
    ので
    2.79
    phine
    2.67
    a
    2.44
    ոն
    2.42
    ल
    2.41
    داد
    2.38
    鹕
    2.35
    Act Density 0.033%

    No Known Activations