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

    Neuronpedia

    INDEX
    Explanations

    are/you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     series
    -0.07
    unsubscribe
    -0.07
    weg
    -0.06
    ...............
    -0.06
     helped
    -0.06
    olleyError
    -0.06
     Seeder
    -0.06
    的感觉
    -0.06
    怍
    -0.06
    forcements
    -0.06
    POSITIVE LOGITS
    _dot
    0.07
    ⚄
    0.06
     TCHAR
    0.06
     regulation
    0.06
    琊
    0.06
     Tay
    0.06
    凭证
    0.06
    Pure
    0.06
    테
    0.06
     caract
    0.06
    Act Density 0.088%

    No Known Activations