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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     airline
    -0.06
     molecules
    -0.06
    computer
    -0.06
    Compact
    -0.06
     oxygen
    -0.06
     laat
    -0.06
     weighting
    -0.05
     gz
    -0.05
    -categories
    -0.05
     Κύπ
    -0.05
    POSITIVE LOGITS
    getClass
    0.07
    тик
    0.07
    _UUID
    0.07
    ▍▍▍▍▍▍▍▍▍▍▍▍▍▍▍▍
    0.06
     trait
    0.06
    checkout
    0.06
    .LEADING
    0.06
    倒
    0.06
    노출
    0.06
    CardBody
    0.06
    Act Density 0.014%

    No Known Activations