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

    Neuronpedia

    INDEX
    Explanations

    generate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     talent
    -0.07
    ENCIL
    -0.07
    莩
    -0.07
    仅供
    -0.06
     exquisite
    -0.06
    漫步
    -0.06
     celebrity
    -0.06
     meaning
    -0.06
    esModule
    -0.06
    UInteger
    -0.06
    POSITIVE LOGITS
    お
    0.08
    郑
    0.07
     Pont
    0.07
    oct
    0.07
     versa
    0.07
    �
    0.06
    いません
    0.06
     Townsend
    0.06
     CharSet
    0.06
     gsi
    0.06
    Act Density 0.002%

    No Known Activations