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

    Neuronpedia

    INDEX
    Explanations

    Causation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ал
    -0.07
    披
    -0.06
    ẩm
    -0.06
    (resp
    -0.06
     aun
    -0.06
    /preferences
    -0.06
    海棠
    -0.06
    держ
    -0.06
    宠
    -0.06
    Measurement
    -0.06
    POSITIVE LOGITS
     listings
    0.07
    Local
    0.07
     dette
    0.07
    ложен
    0.07
    	exports
    0.07
    сор
    0.07
    .fft
    0.07
    |M
    0.06
    싯
    0.06
     demonstr
    0.06
    Act Density 0.008%

    No Known Activations