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

    Neuronpedia

    INDEX
    Explanations

    mocking names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Minh
    -0.08
     inex
    -0.08
     madu
    -0.07
     الخيار
    -0.07
     radar
    -0.07
     embargo
    -0.07
     experimented
    -0.07
     exploded
    -0.07
     miles
    -0.07
     разм
    -0.07
    POSITIVE LOGITS
    (actual
    0.08
     Atual
    0.08
    402
    0.08
    (result
    0.08
     Taw
    0.08
    ต่าง
    0.07
    (register
    0.07
    .assign
    0.07
    _register
    0.07
    _actual
    0.07
    Act Density 0.002%

    No Known Activations