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

    Neuronpedia

    INDEX
    Explanations

    aluminum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝖆
    2.20
    𝖔
    2.20
    𝖊
    2.16
    ент
    2.09
    يه
    2.08
    likle
    2.02
    ান
    1.95
    𝖑
    1.88
    𝖓
    1.88
    ানন্দ
    1.86
    POSITIVE LOGITS
     возможность
    2.05
     Banyak
    1.96
     আনোয়ার
    1.94
     отмеча
    1.93
     доста
    1.92
     desenvolv
    1.86
    т
    1.86
     созда
    1.81
    𝐀
    1.81
     Aan
    1.80
    Act Density 0.194%

    No Known Activations