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

    Neuronpedia

    INDEX
    Explanations

    attrs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manipulate
    -0.08
     Yep
    -0.07
    052
    -0.07
     Kush
    -0.07
    .”
    -0.07
     香
    -0.07
     unregister
    -0.06
    _manual
    -0.06
    erokee
    -0.06
     SAND
    -0.06
    POSITIVE LOGITS
     attrs
    0.09
    Portable
    0.07
    terraform
    0.07
    installer
    0.06
     libertin
    0.06
    _DRIVER
    0.06
    rowsers
    0.06
    _Des
    0.06
    ीवन
    0.06
    iams
    0.06
    Act Density 0.000%

    No Known Activations