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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     имп
    -0.06
     thấy
    -0.06
     foam
    -0.06
     shipment
    -0.06
     jq
    -0.06
    .ADD
    -0.06
    avail
    -0.06
     ngành
    -0.06
    조
    -0.06
     borrowed
    -0.06
    POSITIVE LOGITS
     čas
    0.06
    esz
    0.06
     нат
    0.06
    ând
    0.06
    ORT
    0.06
    fel
    0.06
     práce
    0.06
     SYS
    0.06
     Lieutenant
    0.06
    EW
    0.06
    Act Density 0.019%

    No Known Activations