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
     withStyles
    -0.07
    aces
    -0.06
     ayant
    -0.06
     Pregnancy
    -0.06
    .stringify
    -0.06
    kle
    -0.06
     зави
    -0.06
    ecký
    -0.06
    imetype
    -0.06
     Trusted
    -0.06
    POSITIVE LOGITS
    _buy
    0.07
     december
    0.06
    셀
    0.06
     الأف
    0.06
     boutique
    0.06
    وروب
    0.06
     -->↵↵↵
    0.06
    .getService
    0.06
     %>
    0.06
    _original
    0.06
    Act Density 0.055%

    No Known Activations