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

    Neuronpedia

    INDEX
    Explanations

    Comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    datasets
    -0.07
     sucess
    -0.07
     pods
    -0.06
    wu
    -0.06
    anta
    -0.06
    Paste
    -0.06
    archive
    -0.06
     interoper
    -0.06
     Glacier
    -0.06
    มาร
    -0.06
    POSITIVE LOGITS
    >D
    0.07
    块
    0.06
    }$
    0.06
    .setPosition
    0.06
     zač
    0.06
     sammen
    0.06
     -=
    0.06
    <=$
    0.06
    <=
    0.06
    Tit
    0.06
    Act Density 0.055%

    No Known Activations