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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .masks
    -0.07
    荒
    -0.07
     Memorial
    -0.07
     deleteUser
    -0.07
    䴥
    -0.07
    eneral
    -0.06
    relude
    -0.06
    qb
    -0.06
    大理石
    -0.06
     больш
    -0.06
    POSITIVE LOGITS
    ريع
    0.07
     Ap
    0.07
    овых
    0.07
    .DoesNotExist
    0.07
     ounces
    0.07
    开发区
    0.07
    appointment
    0.06
    //↵
    0.06
    führt
    0.06
     sided
    0.06
    Act Density 0.001%

    No Known Activations