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

    Neuronpedia

    INDEX
    Explanations

    result

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    性能
    -0.07
     tank
    -0.07
    ighb
    -0.06
     bush
    -0.06
     "-",
    -0.06
     ng
    -0.06
     vos
    -0.06
    840
    -0.06
     capitalize
    -0.06
     handicap
    -0.06
    POSITIVE LOGITS
     result
    0.14
    Result
    0.12
    	result
    0.11
     Result
    0.10
     resultado
    0.10
     results
    0.10
    _result
    0.09
    (Result
    0.09
    .result
    0.09
    :result
    0.09
    Act Density 0.022%

    No Known Activations