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

    Neuronpedia

    INDEX
    Explanations

    python tkinter ttk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rich
    0.42
    τερ
    0.40
     fullness
    0.39
    auction
    0.39
    tough
    0.39
     σκ
    0.38
    Extreme
    0.38
     auctions
    0.38
    network
    0.37
    parts
    0.37
    POSITIVE LOGITS
     wrześ
    0.44
     సాం
    0.39
    isVideoRecording
    0.39
     체크
    0.38
     Voters
    0.37
     organizers
    0.36
     경찰
    0.36
     arranges
    0.35
     పోలీసులు
    0.35
     ndị
    0.35
    Act Density 0.000%

    No Known Activations