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

    Neuronpedia

    INDEX
    Explanations

    mass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hari
    -0.07
    (PyObject
    -0.06
     reach
    -0.06
     prevState
    -0.06
     والم
    -0.06
    ôm
    -0.06
     Instances
    -0.06
    _Line
    -0.06
    .newaxis
    -0.06
     wx
    -0.06
    POSITIVE LOGITS
     chin
    0.07
     RULE
    0.07
    fresh
    0.07
    Brain
    0.06
    alone
    0.06
     Alice
    0.06
    Fed
    0.06
    Seeder
    0.06
     overpower
    0.06
    Prem
    0.06
    Act Density 0.006%

    No Known Activations