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

    Neuronpedia

    INDEX
    Explanations

    online reputation management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purification
    -0.07
    旁
    -0.07
    지도
    -0.06
     ور
    -0.06
    vý
    -0.06
     infected
    -0.06
     gratuit
    -0.06
    doing
    -0.06
    ↵            ↵
    -0.06
    ूस
    -0.06
    POSITIVE LOGITS
     Throw
    0.06
    currentUser
    0.06
    _ACCESS
    0.06
    Michelle
    0.06
    (worker
    0.06
    _ORIGIN
    0.06
    lifetime
    0.06
     moyen
    0.06
     Origin
    0.06
     меч
    0.06
    Act Density 0.019%

    No Known Activations