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

    Neuronpedia

    INDEX
    Explanations

    Reduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Controller
    -0.08
     Saunders
    -0.07
     바랍니다
    -0.07
    (abs
    -0.07
     halves
    -0.07
     popularity
    -0.07
    aclass
    -0.07
     favored
    -0.07
    小时
    -0.07
     mëny
    -0.07
    POSITIVE LOGITS
     estaremos
    0.09
     hoeven
    0.09
     overheating
    0.08
     headaches
    0.08
    458
    0.08
     estará
    0.08
     chance
    0.07
     resentment
    0.07
     podrás
    0.07
     thermal
    0.07
    Act Density 0.033%

    No Known Activations