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

    Neuronpedia

    INDEX
    Explanations

    black hole physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     planned
    -0.08
    ись
    -0.07
     approaching
    -0.07
    rode
    -0.07
     vậy
    -0.07
     person
    -0.07
     Circle
    -0.06
    (program
    -0.06
     patterned
    -0.06
     fores
    -0.06
    POSITIVE LOGITS
     crim
    0.08
    _except
    0.08
     Ogre
    0.08
     nort
    0.08
    élé
    0.08
    新品
    0.08
     Traits
    0.08
     секунд
    0.08
    ล็
    0.08
     ONLY
    0.07
    Act Density 0.000%

    No Known Activations