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
    贴
    -0.07
    _locked
    -0.07
     recognizes
    -0.06
    /H
    -0.06
    pressed
    -0.06
     absorbed
    -0.06
    mediately
    -0.06
    _ly
    -0.06
     awful
    -0.06
     کیلومتر
    -0.06
    POSITIVE LOGITS
     fecha
    0.07
     Tart
    0.07
     Độ
    0.06
     theological
    0.06
    ПО
    0.06
    Bạn
    0.06
     Lincoln
    0.06
     seb
    0.06
     Záp
    0.06
    );↵↵↵↵↵
    0.06
    Act Density 0.053%

    No Known Activations