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

    Neuronpedia

    INDEX
    Explanations

    programmed to be safe and helpful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kd
    0.40
     ดาว
    0.38
     কের
    0.37
     Tabs
    0.36
     Scot
    0.36
    辋
    0.36
     covalent
    0.35
    よかった
    0.35
    燊
    0.35
    ंक
    0.34
    POSITIVE LOGITS
    Anthony
    0.43
    Le
    0.43
     பெ
    0.39
     Anthony
    0.38
    Eh
    0.38
    ที่จะ
    0.36
    Or
    0.36
    pellier
    0.36
     chow
    0.35
    BufferedReader
    0.35
    Act Density 0.027%

    No Known Activations