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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    งอย
    -0.07
     очень
    -0.07
    ’B
    -0.07
     나타
    -0.06
     catapult
    -0.06
     riêng
    -0.06
     seriously
    -0.06
     فقط
    -0.06
     Directorate
    -0.06
     capitals
    -0.06
    POSITIVE LOGITS
    .Copy
    0.07
    _reaction
    0.07
    INARY
    0.06
     competitors
    0.06
    <Object
    0.06
     loser
    0.06
    reader
    0.06
    .setContentType
    0.06
    (Tree
    0.06
    --
↵
    0.06
    Act Density 0.000%

    No Known Activations