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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medios
    -0.06
     отмеч
    -0.06
     sean
    -0.06
    TestFixture
    -0.06
     años
    -0.06
    「そう
    -0.06
    "go
    -0.06
     mujeres
    -0.05
     постоянно
    -0.05
     grpc
    -0.05
    POSITIVE LOGITS
     Electrical
    0.07
    Tr
    0.07
    อกาส
    0.07
    (users
    0.07
    (Blueprint
    0.07
    GORITHM
    0.07
    .Exists
    0.07
    ون
    0.06
    _buf
    0.06
     decoded
    0.06
    Act Density 0.000%

    No Known Activations