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

    Neuronpedia

    INDEX
    Explanations

    No

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Printer
    -0.07
     canal
    -0.07
     société
    -0.07
     Queen
    -0.07
     kidn
    -0.07
     Station
    -0.06
     geographic
    -0.06
     Fantasy
    -0.06
     llegar
    -0.06
    Station
    -0.06
    POSITIVE LOGITS
    となる
    0.07
    문을
    0.06
    erving
    0.06
    つけ
    0.06
    genden
    0.06
    べて
    0.06
     Например
    0.06
    िप
    0.06
    ischen
    0.06
    ])/
    0.06
    Act Density 0.006%

    No Known Activations