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

    Neuronpedia

    INDEX
    Explanations

    sunshine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mall
    -0.06
     CC
    -0.06
     Loft
    -0.06
     kayak
    -0.06
     loft
    -0.06
    entes
    -0.06
    빌
    -0.06
     Pastor
    -0.06
    	Long
    -0.06
    lod
    -0.06
    POSITIVE LOGITS
    (CONFIG
    0.08
    _input
    0.07
     тру
    0.07
     uplifting
    0.07
     Sunshine
    0.07
     China
    0.06
     specifies
    0.06
    Promise
    0.06
    $input
    0.06
     defenders
    0.06
    Act Density 0.002%

    No Known Activations