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

    Neuronpedia

    INDEX
    Explanations

    headlights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เมน
    -0.07
    加息
    -0.07
     teasing
    -0.07
     قض
    -0.07
     Mundo
    -0.07
    ジョ
    -0.07
    orre
    -0.07
     stared
    -0.07
     Jen
    -0.06
     fragmentManager
    -0.06
    POSITIVE LOGITS
    พลาด
    0.07
    Length
    0.07
     Ability
    0.07
     tainted
    0.07
    ivation
    0.07
    (colors
    0.07
     inclusion
    0.07
     detect
    0.07
    上年同期
    0.07
     droit
    0.07
    Act Density 0.005%

    No Known Activations