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

    Neuronpedia

    INDEX
    Explanations

    gap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ج
    1.41
    ли
    1.35
    ে
    1.22
    fptr
    1.11
     forgo
    1.11
    ,*/}*.
    1.09
    SpriteCollision
    1.08
    ட்சத்திர
    1.07
    ℠
    1.07
    httpClient
    1.06
    POSITIVE LOGITS
    一个
    1.11
    ır
    1.09
    на
    1.04
    ıyla
    1.04
    不是
    1.02
    ín
    0.98
    です
    0.98
    }])
    0.97
    を実現
    0.96
    ৯
    0.96
    Act Density 0.003%

    No Known Activations