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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XCT
    -0.07
    Nat
    -0.07
     cinemat
    -0.07
    _bundle
    -0.07
    /high
    -0.06
    )}}
    -0.06
     Ald
    -0.06
    ephy
    -0.06
    _rule
    -0.06
     rij
    -0.06
    POSITIVE LOGITS
      ↵↵
    0.07
     eslint
    0.06
     teleport
    0.06
     stirring
    0.06
    angular
    0.06
     orally
    0.06
     stirred
    0.06
     unut
    0.06
     pitcher
    0.06
    ?";↵
    0.06
    Act Density 0.001%

    No Known Activations