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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hai
    -0.07
    _Search
    -0.07
    _pix
    -0.06
    一些
    -0.06
    ains
    -0.06
    -dev
    -0.06
    Analytics
    -0.06
    Down
    -0.06
    -less
    -0.06
    quette
    -0.06
    POSITIVE LOGITS
    Local
    0.06
    affen
    0.06
     cj
    0.06
    ".
    0.06
    „M
    0.06
    }});↵
    0.06
     districts
    0.06
    岡
    0.06
     Lake
    0.06
     }↵
    0.06
    Act Density 0.216%

    No Known Activations