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
    hou
    -0.07
     disclosure
    -0.07
     Alzheimer
    -0.07
    Employees
    -0.06
    (n
    -0.06
     Measurements
    -0.06
     hacker
    -0.06
     Shanghai
    -0.06
     upside
    -0.06
     Anatomy
    -0.06
    POSITIVE LOGITS
     Donne
    0.07
    acja
    0.07
     ihtiyac
    0.07
     Basil
    0.07
    �
    0.07
     فصل
    0.06
     browsing
    0.06
     sanki
    0.06
    ındaki
    0.06
     rgba
    0.06
    Act Density 0.162%

    No Known Activations