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

    Neuronpedia

    INDEX
    Explanations

    imes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cd
    -0.07
    遠
    -0.07
    oxid
    -0.07
     ödem
    -0.07
    mine
    -0.06
     piger
    -0.06
    _disk
    -0.06
    ินด
    -0.06
     úspěš
    -0.06
     nejlepší
    -0.06
    POSITIVE LOGITS
    "
↵
    0.06
     뜻
    0.06
     bíl
    0.06
    Eye
    0.06
     ​​​
    0.06
    ทาง
    0.06
     ؟
    0.06
     StringComparison
    0.06
     automatically
    0.06
    .crypto
    0.06
    Act Density 0.001%

    No Known Activations