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

    Neuronpedia

    INDEX
    Explanations

    load DataFrame

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     günd
    0.68
     верх
    0.68
    pop
    0.67
     सामूहिक
    0.67
     الخارجية
    0.67
    Raleway
    0.66
     kahit
    0.66
    जिंग
    0.65
     उपराष्ट्रपति
    0.64
    chern
    0.64
    POSITIVE LOGITS
     محر
    0.63
     Episode
    0.60
     Episodes
    0.59
    >?
    0.58
     alloys
    0.58
    驱动
    0.57
     Landon
    0.57
     episodes
    0.57
     alloy
    0.57
     Antibody
    0.57
    Act Density 0.001%

    No Known Activations