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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >).
    -0.08
     pige
    -0.07
    علوم
    -0.07
    ораз
    -0.07
    istrat
    -0.07
    �
    -0.07
    ">',↵
    -0.06
    》，
    -0.06
    RIA
    -0.06
     iVar
    -0.06
    POSITIVE LOGITS
     ViewBag
    0.06
    彻
    0.06
     seizing
    0.06
    /style
    0.06
    destroy
    0.06
    spec
    0.06
    (prefix
    0.06
     Northwestern
    0.06
    (/
    0.05
    िक
    0.05
    Act Density 0.034%

    No Known Activations