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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Autonomous
    -0.06
    ­ing
    -0.06
     identify
    -0.06
    fid
    -0.06
     inaccessible
    -0.06
     Niger
    -0.06
    GLE
    -0.06
     parliamentary
    -0.06
    奧
    -0.06
    lobby
    -0.06
    POSITIVE LOGITS
    ERING
    0.07
     ApplicationController
    0.07
     $__
    0.07
    action
    0.06
    англ
    0.06
     fecha
    0.06
    -sc
    0.06
     widespread
    0.06
    ��
    0.06
    Ethernet
    0.06
    Act Density 0.011%

    No Known Activations