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

    Neuronpedia

    INDEX
    Explanations

    code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    serialization
    -0.07
     Beijing
    -0.07
    галі
    -0.06
    _Surface
    -0.06
    parity
    -0.06
     folly
    -0.06
     Gloss
    -0.06
     XCTAssert
    -0.06
    lığına
    -0.06
    	inter
    -0.06
    POSITIVE LOGITS
     Marcus
    0.07
    .↵↵↵↵↵
    0.07
     opting
    0.06
     [\
    0.06
    miner
    0.06
     PE
    0.06
     tumors
    0.06
    Marcus
    0.06
     perpetr
    0.06
     SignUp
    0.06
    Act Density 0.000%

    No Known Activations