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

    Neuronpedia

    INDEX
    Explanations

    updated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    气温
    -0.08
    columns
    -0.08
    _EXIT
    -0.07
     salary
    -0.07
    政务
    -0.07
    _initialized
    -0.07
    Get
    -0.07
    ct
    -0.07
     diagonal
    -0.07
    启
    -0.07
    POSITIVE LOGITS
     condos
    0.07
    ulta
    0.07
    .backup
    0.07
    umping
    0.06
    _rat
    0.06
    עיצוב
    0.06
    ょ
    0.06
     culpa
    0.06
    压实
    0.06
     surfing
    0.06
    Act Density 0.005%

    No Known Activations