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

    Neuronpedia

    INDEX
    Explanations

    say ,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ENGINEERING
    0.49
     що
    0.48
     non
    0.43
     све
    0.43
     universally
    0.43
     வண்ணப்பூ
    0.42
    வத
    0.42
     che
    0.41
     kub
    0.41
     STORAGE
    0.41
    POSITIVE LOGITS
    Allows
    0.37
    ]}/${
    0.37
    лма
    0.36
    >]
    0.36
    Zeneca
    0.36
    ುತ್ತಿರುವ
    0.35
     Fad
    0.35
    Essay
    0.35
    Templ
    0.35
    Fury
    0.34
    Act Density 0.000%

    No Known Activations