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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     registering
    -0.07
    烯
    -0.06
    处
    -0.06
     an
    -0.06
    Beans
    -0.06
    CED
    -0.06
     released
    -0.06
    вести
    -0.06
     pellet
    -0.06
    lings
    -0.06
    POSITIVE LOGITS
     veil
    0.08
     Arbitrary
    0.08
     Operational
    0.07
         ↵
    0.07
    旖
    0.07
    _algorithm
    0.07
    .Lock
    0.07
     Privacy
    0.07
     Ontario
    0.06
     nền
    0.06
    Act Density 0.023%

    No Known Activations