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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     visitor
    -0.07
    .assertIsInstance
    -0.07
     terrified
    -0.07
    西侧
    -0.07
     swelling
    -0.07
    投票
    -0.06
     resistor
    -0.06
     positivity
    -0.06
     userData
    -0.06
    (AT
    -0.06
    POSITIVE LOGITS
     пунк
    0.07
    onic
    0.07
    fäll
    0.07
    ốn
    0.07
     cumpl
    0.07
    넝
    0.07
    types
    0.07
    erna
    0.07
    плачива
    0.07
    嶦
    0.07
    Act Density 0.034%

    No Known Activations