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

    Neuronpedia

    INDEX
    Explanations

    forms of "are"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (select
    -0.08
    hemm
    -0.08
    nub
    -0.08
    (ans
    -0.08
    秘书
    -0.07
    verbosity
    -0.07
    verwaltung
    -0.07
    Secretary
    -0.07
     complains
    -0.07
    ेब
    -0.07
    POSITIVE LOGITS
    უნ
    0.08
     preceded
    0.08
     pulse
    0.08
     сила
    0.08
     друг
    0.08
     हवा
    0.08
     happening
    0.08
    幸福
    0.07
     powerful
    0.07
     પ્રેમ
    0.07
    Act Density 0.017%

    No Known Activations