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

    Neuronpedia

    INDEX
    Explanations

    Homes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fast
    -0.07
     tumble
    -0.07
    "—
    -0.07
     exem
    -0.06
     aff
    -0.06
     fall
    -0.06
     todo
    -0.06
     doubt
    -0.06
    >c
    -0.06
     refining
    -0.06
    POSITIVE LOGITS
     MMA
    0.06
    replacement
    0.06
     injuring
    0.06
     özel
    0.06
    лей
    0.06
    <Customer
    0.06
     Fresno
    0.06
    oran
    0.06
    циональ
    0.06
    NY
    0.06
    Act Density 0.000%

    No Known Activations