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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wolverine
    -0.07
    posting
    -0.06
     Alert
    -0.06
    ований
    -0.06
    kke
    -0.06
    aşa
    -0.06
     verschill
    -0.06
     defaults
    -0.06
    userManager
    -0.06
    ┃
    -0.06
    POSITIVE LOGITS
    .period
    0.07
     nghiên
    0.07
    cosity
    0.07
    	length
    0.06
     warto
    0.06
     době
    0.06
     京
    0.06
     regulators
    0.06
    ICENSE
    0.06
     Kiev
    0.06
    Act Density 0.015%

    No Known Activations