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

    Neuronpedia

    INDEX
    Explanations

    crafting and launching soon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    2.14
    ।
    1.90
    ۔
    1.89
     سکے۔
    1.82
    .
    1.80
    یں۔
    1.75
    ።
    1.72
     گا۔
    1.72
    ا۔
    1.71
     گی۔
    1.71
    POSITIVE LOGITS
    ですし
    1.19
    力和
    1.13
    性和
    1.13
    했고
    1.12
    었고
    1.11
    时间和
    1.10
     असून
    1.09
     {},
    1.07
    がなく
    1.01
     있으며
    1.01
    Act Density 1.603%

    No Known Activations