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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ularity
    -0.07
     JW
    -0.07
    rani
    -0.07
    yang
    -0.07
    acity
    -0.07
    oli
    -0.07
     deviation
    -0.07
    Roles
    -0.06
     Ment
    -0.06
     herb
    -0.06
    POSITIVE LOGITS
    .delegate
    0.06
    Gallery
    0.06
     embarrassing
    0.06
    (workspace
    0.06
     Often
    0.06
     exporters
    0.06
     noche
    0.06
    .deepEqual
    0.06
     upgrade
    0.06
     대부분
    0.06
    Act Density 0.019%

    No Known Activations