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

    Neuronpedia

    INDEX
    Explanations

    employment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    系統
    -0.08
    Join
    -0.07
     अम
    -0.07
     Irvine
    -0.07
    commended
    -0.06
    苹果
    -0.06
    (cap
    -0.06
    Drug
    -0.06
     politik
    -0.06
    γωγή
    -0.06
    POSITIVE LOGITS
    _ps
    0.06
     trope
    0.06
     (?,
    0.06
     sorrow
    0.06
    rece
    0.06
     Podcast
    0.06
     (;;
    0.06
     invoice
    0.06
    蜘蛛词
    0.06
    ernote
    0.06
    Act Density 0.063%

    No Known Activations