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

    Neuronpedia

    INDEX
    Explanations

    specific terms and following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propagated
    0.48
     약간
    0.46
     cycling
    0.46
     Wochschr
    0.45
     hiking
    0.45
    。【
    0.45
    ênh
    0.44
     aroused
    0.44
     숫
    0.44
     deducted
    0.43
    POSITIVE LOGITS
    Att
    0.50
    Native
    0.45
    內
    0.44
     असेल
    0.44
    PET
    0.44
    ハウス
    0.43
    焚
    0.43
    Evans
    0.43
     digo
    0.42
    Vict
    0.42
    Act Density 0.001%

    No Known Activations