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

    Neuronpedia

    INDEX
    Explanations

    adjectives preceding nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     milieux
    0.30
     ছুটি
    0.29
     제품
    0.29
     ಉತ್ಪನ್ನ
    0.29
    本作
    0.28
    危機
    0.28
     ഭരണ
    0.28
     splendour
    0.28
     lefty
    0.28
     vários
    0.28
    POSITIVE LOGITS
     (~
    0.30
    /
    0.30
    Proto
    0.28
     (!)
    0.27
    (!)
    0.27
    Modified
    0.27
    +
    0.26
    ,
    0.25
     Virtual
    0.25
    Modify
    0.25
    Act Density 0.042%

    No Known Activations