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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Robotics
    -0.09
    监督
    -0.09
    assim
    -0.08
    报名
    -0.08
     Redes
    -0.08
    勇
    -0.08
     scouting
    -0.08
     Clique
    -0.08
     clique
    -0.08
     التدريب
    -0.08
    POSITIVE LOGITS
    (Http
    0.11
    Response
    0.11
    _response
    0.10
    Http
    0.10
    .response
    0.10
    (Response
    0.10
     emitting
    0.10
     rendering
    0.10
     response
    0.10
    .Response
    0.10
    Act Density 0.008%

    No Known Activations