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

    Neuronpedia

    INDEX
    Explanations

    building, habitat, defined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    阿拉伯
    0.46
     Тере
    0.45
    وعه
    0.44
     announced
    0.43
    合理
    0.43
    创造
    0.42
    izzo
    0.42
     الماء
    0.42
    🧟
    0.42
    ರವಾಗಿ
    0.42
    POSITIVE LOGITS
     feel
    0.44
    ết
    0.44
    씬
    0.42
    n
    0.41
    ên
    0.41
     postdoctoral
    0.41
     spoof
    0.41
     ਨੂੰ
    0.40
    nics
    0.40
    mu
    0.40
    Act Density 0.001%

    No Known Activations