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

    Neuronpedia

    INDEX
    Explanations

    boss employer

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rainment
    0.63
     رنز
    0.63
    繊維
    0.62
    imsy
    0.62
     Rauch
    0.61
    Pyrimidine
    0.60
     دہ
    0.60
     strained
    0.59
     поставить
    0.59
     inc
    0.58
    POSITIVE LOGITS
     boss
    2.72
     Boss
    2.50
    Boss
    2.43
     bosses
    2.39
    boss
    2.33
     BOSS
    2.16
    BOSS
    2.03
     बॉस
    1.95
    ボス
    1.80
     employer
    1.39
    Act Density 0.140%

    No Known Activations