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

    Neuronpedia

    INDEX
    Explanations

    o

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sit
    -0.08
    -Israel
    -0.07
     Initialization
    -0.07
    이션
    -0.07
     ville
    -0.07
     Bool
    -0.06
    irt
    -0.06
    't
    -0.06
    iking
    -0.06
    Vision
    -0.06
    POSITIVE LOGITS
    ————————————————
    0.06
    φυ
    0.06
    .getHours
    0.06
    .setStroke
    0.06
     SHIPPING
    0.06
     elic
    0.06
    .invoice
    0.06
     rearr
    0.06
    睡
    0.06
    负责
    0.06
    Act Density 0.014%

    No Known Activations