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

    Neuronpedia

    INDEX
    Explanations

    service providing referrals and support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     downregulated
    0.33
    Aslamualaikum
    0.31
     eslint
    0.29
     gameOver
    0.28
     summarised
    0.28
     FTIR
    0.28
     tuple
    0.28
     stopwords
    0.28
    전히
    0.27
     downregulation
    0.27
    POSITIVE LOGITS
    programs
    0.32
    program
    0.31
    development
    0.31
     petrochemical
    0.31
    environ
    0.31
     vitality
    0.29
    quickly
    0.29
    योग्य
    0.29
    機会
    0.29
    environment
    0.28
    Act Density 0.077%

    No Known Activations