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

    Neuronpedia

    INDEX
    Explanations

    installing dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emphasize
    0.42
     lyophil
    0.42
     à
    0.40
     emphasized
    0.40
     length
    0.39
     و
    0.38
     bread
    0.38
     versus
    0.38
     தெரிய
    0.38
     మరియు
    0.38
    POSITIVE LOGITS
    ग्रीकल्चर
    0.38
    ständig
    0.38
    SAT
    0.37
    він
    0.36
    just
    0.36
    WALLET
    0.36
    厦
    0.36
     Intelig
    0.36
    ซิต
    0.35
    Uncle
    0.35
    Act Density 0.000%

    No Known Activations