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

    Neuronpedia

    INDEX
    Explanations

    %

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     💪
    0.37
     hailing
    0.29
     fulfilling
    0.29
     endure
    0.28
     Millennials
    0.28
     extraordinaire
    0.28
     resilience
    0.28
     🥰
    0.28
     furthering
    0.28
     https
    0.27
    POSITIVE LOGITS
    Arquivo
    0.31
    Angle
    0.30
    Freq
    0.30
    Deprecated
    0.29
    Nested
    0.29
    Pattern
    0.28
    Initialize
    0.28
    Bump
    0.28
    Accuracy
    0.28
    Query
    0.28
    Act Density 0.041%

    No Known Activations