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

    Neuronpedia

    INDEX
    Explanations

    quantities and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uncomplicated
    -0.09
     некоторое
    -0.08
     depreciation
    -0.08
     relacionados
    -0.08
     misdemeanor
    -0.07
     importantly
    -0.07
     mindre
    -0.07
     cotid
    -0.07
     inay
    -0.07
    izador
    -0.07
    POSITIVE LOGITS
    甚至
    0.11
     Wow
    0.10
    Wow
    0.10
     Teng
    0.09
     unimaginable
    0.09
    Whoa
    0.09
     terrifying
    0.09
     невероят
    0.09
     towering
    0.09
     jopa
    0.09
    Act Density 0.140%

    No Known Activations