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

    Neuronpedia

    INDEX
    Explanations

    After

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ella
    -0.07
    Compound
    -0.07
     passenger
    -0.07
    op
    -0.07
    OP
    -0.06
    驗
    -0.06
     अत
    -0.06
     预
    -0.06
    ОВ
    -0.06
    ags
    -0.06
    POSITIVE LOGITS
    _deg
    0.07
    .AddSingleton
    0.06
     خیلی
    0.06
     giden
    0.06
    かな
    0.06
     kendisini
    0.06
    اخته
    0.06
     merely
    0.06
     normalized
    0.06
     lun
    0.06
    Act Density 0.105%

    No Known Activations