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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RestorePolicy
    0.37
    краё
    0.35
    ясплат
    0.35
    Điều
    0.34
    惀
    0.33
    }"
    0.33
     realtime
    0.33
    лянчук
    0.32
     эмоциона
    0.32
     normativa
    0.32
    POSITIVE LOGITS
     Antarctica
    0.46
     tobacco
    0.45
     the
    0.43
     Dracula
    0.42
     Cleopatra
    0.41
     Napoleon
    0.41
     Beethoven
    0.41
     Persia
    0.41
     chocolate
    0.41
     opium
    0.41
    Act Density 0.179%

    No Known Activations