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
     visitor
    -0.07
    “And
    -0.07
     Liability
    -0.07
    .encrypt
    -0.07
    included
    -0.06
    รม
    -0.06
    "And
    -0.06
     neighbour
    -0.06
    /downloads
    -0.06
     Dispatcher
    -0.06
    POSITIVE LOGITS
    ęż
    0.06
    _loop
    0.06
    oko
    0.06
     Làm
    0.06
    .setData
    0.06
    预
    0.06
     أع
    0.06
    .unpack
    0.06
     gerçekten
    0.06
    EQ
    0.06
    Act Density 0.006%

    No Known Activations