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

    Neuronpedia

    INDEX
    Explanations

    oil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     몸
    -0.07
    етом
    -0.06
    	bus
    -0.06
    RYPTO
    -0.06
    /ros
    -0.06
    不足
    -0.06
    우스
    -0.06
     interrupt
    -0.06
     Brut
    -0.06
    ADATA
    -0.06
    POSITIVE LOGITS
     paramName
    0.07
     Called
    0.06
    Expires
    0.06
     выполн
    0.06
     sud
    0.06
     eylem
    0.06
    nim
    0.06
    Southern
    0.06
    uur
    0.06
     tools
    0.06
    Act Density 0.002%

    No Known Activations