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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Фор
    -0.07
    软件
    -0.07
    GetMethod
    -0.07
    уванні
    -0.06
    ritos
    -0.06
    .security
    -0.06
     ambiente
    -0.06
    λω
    -0.06
    _LOCAL
    -0.06
     آر
    -0.06
    POSITIVE LOGITS
    ’é
    0.08
    Defs
    0.06
    唐
    0.06
     INTER
    0.06
    *log
    0.06
    :e
    0.06
     hw
    0.06
    _plain
    0.06
     '".$
    0.06
     teacher
    0.06
    Act Density 0.024%

    No Known Activations