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

    Neuronpedia

    INDEX
    Explanations

    HMAC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     res
    -0.07
     MAX
    -0.07
    .art
    -0.07
     rou
    -0.07
    �
    -0.07
     ses
    -0.07
    unist
    -0.07
    arn
    -0.07
    登山
    -0.07
    start
    -0.07
    POSITIVE LOGITS
    policy
    0.08
     Macedonia
    0.07
    Secondary
    0.07
     headquartered
    0.07
    ‗
    0.07
    ▭
    0.07
    ⋋
    0.07
    yscale
    0.07
     Collaboration
    0.07
    회사
    0.07
    Act Density 0.001%

    No Known Activations