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

    Neuronpedia

    INDEX
    Explanations

    parentheses/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GameObject
    -0.08
     whales
    -0.07
    .Physics
    -0.07
     GNOME
    -0.07
     Beach
    -0.06
     peaked
    -0.06
    GameObject
    -0.06
     Physics
    -0.06
    Factor
    -0.06
     elections
    -0.06
    POSITIVE LOGITS
    ै?↵
    0.06
     recycle
    0.06
    출장샵
    0.06
    __);↵
    0.06
    欣
    0.06
    ۲۰۲
    0.06
    (article
    0.06
     """↵↵
    0.05
     uri
    0.05
    大
    0.05
    Act Density 0.024%

    No Known Activations