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

    Neuronpedia

    INDEX
    Explanations

    References to people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    さん
    -0.07
    	flags
    -0.06
     gel
    -0.06
    波
    -0.06
    onest
    -0.06
    _tiles
    -0.06
     mange
    -0.06
     binds
    -0.06
     ULONG
    -0.06
     ngang
    -0.06
    POSITIVE LOGITS
     improving
    0.07
     aggregate
    0.07
    '])[
    0.06
     impairment
    0.06
    /team
    0.06
    >manual
    0.06
    -pro
    0.06
     improve
    0.06
     Ade
    0.06
     verbose
    0.06
    Act Density 0.140%

    No Known Activations