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

    Neuronpedia

    INDEX
    Explanations

    analysis and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ování
    0.49
    chievement
    0.47
    edLeft
    0.46
    énagement
    0.46
    urbation
    0.44
    awks
    0.44
    娠
    0.44
    ുള്ള
    0.43
    െങ്കില്‍
    0.43
    伟大
    0.43
    POSITIVE LOGITS
    r
    0.54
    n
    0.50
    ILL
    0.48
    a
    0.46
     mixes
    0.44
    t
    0.44
    MS
    0.43
    ADY
    0.43
    s
    0.43
    BOOK
    0.42
    Act Density 0.001%

    No Known Activations