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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -my
    -0.07
     py
    -0.06
    Jamie
    -0.06
    ads
    -0.06
     diplomacy
    -0.06
     suppose
    -0.06
    Evaluate
    -0.06
    ­tion
    -0.06
    tsy
    -0.06
     analogue
    -0.06
    POSITIVE LOGITS
     fren
    0.07
    BagConstraints
    0.07
    잔
    0.06
     düşman
    0.06
    _Tree
    0.06
     fuck
    0.06
     notifyDataSetChanged
    0.06
    .getTag
    0.06
     MacOS
    0.06
     seçenek
    0.06
    Act Density 0.024%

    No Known Activations