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

    Neuronpedia

    INDEX
    Explanations

    boss or manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ండె
    0.71
    াবণ
    0.66
    ethoxy
    0.65
    askets
    0.65
     componentWill
    0.64
    ⴰ
    0.63
    ᠶ
    0.63
    asket
    0.62
    ᠴ
    0.62
     청바
    0.62
    POSITIVE LOGITS
     boss
    2.96
     employer
    2.56
     bosses
    2.56
     master
    2.55
     Boss
    2.51
    Boss
    2.51
    boss
    2.44
     Master
    2.37
     masters
    2.28
    master
    2.25
    Act Density 0.142%

    No Known Activations