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

    Neuronpedia

    INDEX
    Explanations

    Greek letters and Arabic characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decidedly
    0.92
     plethora
    0.89
    テゴ
    0.89
     ramai
    0.89
     pericol
    0.89
     cea
    0.87
     problematic
    0.86
     darn
    0.86
    ि
    0.86
     diduga
    0.85
    POSITIVE LOGITS
    و
    1.28
    άλ
    1.17
    ق
    1.13
    د
    1.08
    Accordion
    1.05
    Gym
    1.05
    ógrafo
    1.05
    Zoom
    1.04
    ه
    1.04
    Memory
    1.02
    Act Density 0.035%

    No Known Activations