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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moderated
    -0.07
    _server
    -0.06
    (folder
    -0.06
    assessment
    -0.06
     question
    -0.06
     epith
    -0.06
     experimental
    -0.06
    cars
    -0.06
    зі
    -0.06
     careful
    -0.06
    POSITIVE LOGITS
    ronics
    0.06
    Ctrl
    0.06
    OCR
    0.06
    RB
    0.06
    ampoo
    0.06
    INU
    0.06
     Telerik
    0.06
    .fade
    0.06
    ark
    0.06
     BH
    0.06
    Act Density 0.076%

    No Known Activations