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

    Neuronpedia

    INDEX
    Explanations

    descriptive or comparative words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wszystkie
    0.43
     antigua
    0.37
     usan
    0.36
     velmi
    0.36
     besta
    0.36
     Alemanha
    0.35
    Az
    0.35
     многочис
    0.35
    credibly
    0.35
     całkow
    0.35
    POSITIVE LOGITS
     timestamp
    0.31
     trajectory
    0.29
    后续
    0.29
     preclinical
    0.28
     AppDelegate
    0.28
    msubsup
    0.28
     用于
    0.27
     preliminary
    0.27
     context
    0.27
    组件
    0.27
    Act Density 0.046%

    No Known Activations