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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xff
    -0.07
     choices
    -0.06
     lends
    -0.06
     siz
    -0.06
     сад
    -0.06
    .marker
    -0.06
     nic
    -0.06
     days
    -0.06
     Construction
    -0.06
    _callbacks
    -0.06
    POSITIVE LOGITS
    吸
    0.06
     External
    0.06
    -President
    0.06
     Demand
    0.06
    _individual
    0.06
    Class
    0.06
     audit
    0.06
     Đào
    0.06
    (defun
    0.06
     Kag
    0.06
    Act Density 0.033%

    No Known Activations