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

    Neuronpedia

    INDEX
    Explanations

    refunds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "")
↵
    -0.07
     CHK
    -0.06
    아
    -0.06
    strike
    -0.06
     Memorial
    -0.06
    "^
    -0.06
    сий
    -0.06
    طور
    -0.06
    .Th
    -0.06
     &,
    -0.06
    POSITIVE LOGITS
     khó
    0.07
    _ble
    0.07
    概
    0.07
    Benefits
    0.07
    टन
    0.06
     decoded
    0.06
     reunited
    0.06
     Lux
    0.06
     Sioux
    0.06
     sebe
    0.06
    Act Density 0.003%

    No Known Activations