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

    Neuronpedia

    INDEX
    Explanations

    weather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (£
    -0.07
     Tar
    -0.07
    ⌦
    -0.07
     Kush
    -0.06
    אל
    -0.06
     Pis
    -0.06
    NAS
    -0.06
     있는데
    -0.06
     happiness
    -0.06
    𝑬
    -0.06
    POSITIVE LOGITS
    .weather
    0.08
    	DWORD
    0.08
    手艺
    0.07
    Weather
    0.07
    _METHOD
    0.07
     coeffs
    0.07
     weather
    0.07
    评委
    0.07
    美德公司
    0.07
     Static
    0.07
    Act Density 0.011%

    No Known Activations