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

    Neuronpedia

    INDEX
    Explanations

    geometry problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chemotherapy
    -0.09
     biops
    -0.09
     structured
    -0.08
    .files
    -0.08
     colonial
    -0.08
    (files
    -0.08
     files
    -0.08
     Structured
    -0.08
     thrust
    -0.08
     farming
    -0.08
    POSITIVE LOGITS
    成立
    0.10
     circle
    0.09
    Circle
    0.09
    _circle
    0.09
     �
    0.09
    circle
    0.09
    ircle
    0.09
     ellipse
    0.09
     voli
    0.08
     راب
    0.08
    Act Density 0.023%

    No Known Activations