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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advertiser
    -0.07
    miş
    -0.06
     nej
    -0.06
     calloc
    -0.06
    STALL
    -0.06
    來
    -0.06
    Things
    -0.06
    泊
    -0.06
    ister
    -0.06
     договор
    -0.06
    POSITIVE LOGITS
     Roc
    0.07
     Equ
    0.07
     Hiring
    0.06
     Ort
    0.06
    (position
    0.06
     ControllerBase
    0.06
    ='',↵
    0.06
    운드
    0.06
     Labour
    0.06
    /math
    0.06
    Act Density 0.002%

    No Known Activations