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

    Neuronpedia

    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    resse
    -0.07
     فرو
    -0.06
    utivo
    -0.06
    ึง
    -0.06
    مد
    -0.06
    (com
    -0.06
    ixed
    -0.06
     SAVE
    -0.06
    .EventHandler
    -0.06
     Saved
    -0.06
    POSITIVE LOGITS
     install
    0.07
    method
    0.07
     ◆
    0.07
     propTypes
    0.06
     randomly
    0.06
    碎
    0.06
    assertSame
    0.06
     explain
    0.06
     statically
    0.06
    	Random
    0.06
    Act Density 0.001%

    No Known Activations