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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Courtesy
    -0.07
    .fi
    -0.06
    ición
    -0.06
     Power
    -0.06
    ує
    -0.06
    Converter
    -0.06
    ('#
    -0.06
     Sem
    -0.06
     законодатель
    -0.06
    .ToUpper
    -0.06
    POSITIVE LOGITS
     opera
    0.07
     لق
    0.07
     Tristan
    0.06
    ης
    0.06
     Indeed
    0.06
    .bulk
    0.06
     sketch
    0.06
    555
    0.06
     빨
    0.06
    %).↵↵
    0.06
    Act Density 0.008%

    No Known Activations