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

    Neuronpedia

    INDEX
    Explanations

    finding information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generalized
    0.42
     gewährle
    0.42
     избира
    0.41
     variabile
    0.41
    adjustment
    0.40
    耐
    0.39
     ظرف
    0.38
     роль
    0.38
    டியோ
    0.38
    0.38
    POSITIVE LOGITS
    Website
    0.71
     where
    0.66
     website
    0.66
     Website
    0.64
     홈페이지
    0.64
     Documentation
    0.63
     Learn
    0.61
     learn
    0.60
    Learn
    0.60
     documentation
    0.59
    Act Density 0.009%

    No Known Activations