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

    Neuronpedia

    INDEX
    Explanations

    "can" and "but"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tickets
    -0.07
    Um
    -0.07
    ตำ
    -0.07
    .menuStrip
    -0.07
    WH
    -0.06
    ảy
    -0.06
    Henry
    -0.06
    dance
    -0.06
    Pets
    -0.06
    %X
    -0.06
    POSITIVE LOGITS
     neural
    0.07
     Candid
    0.07
     swapping
    0.07
     completeness
    0.06
     volts
    0.06
     Framework
    0.06
     Injury
    0.06
    /code
    0.06
     test
    0.06
     rám
    0.06
    Act Density 0.080%

    No Known Activations