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

    Neuronpedia

    INDEX
    Explanations

    delivery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dirt
    -0.07
    _FAST
    -0.07
    PRICE
    -0.06
     keer
    -0.06
    公園
    -0.06
     XL
    -0.06
     before
    -0.06
    UTIL
    -0.06
    osopher
    -0.06
     setId
    -0.06
    POSITIVE LOGITS
     menu
    0.07
     teaching
    0.07
     ​
    0.07
     horribly
    0.06
     Edu
    0.06
    し
    0.06
     zich
    0.06
     cał
    0.06
     Eyes
    0.06
    itez
    0.06
    Act Density 0.042%

    No Known Activations