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

    Neuronpedia

    INDEX
    Explanations

    ownership

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     depiction
    -0.07
     Michigan
    -0.07
    orque
    -0.07
    突出问题
    -0.07
    马克
    -0.07
     SetUp
    -0.07
     Bris
    -0.06
     文件
    -0.06
    /connect
    -0.06
    מצרים
    -0.06
    POSITIVE LOGITS
     widely
    0.08
     ire
    0.07
    剕
    0.07
     y
    0.06
    耐心
    0.06
    畴
    0.06
    vt
    0.06
    automation
    0.06
    (IF
    0.06
     pod
    0.06
    Act Density 0.086%

    No Known Activations