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

    Neuronpedia

    INDEX
    Explanations

    among

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ================================================
    -0.07
    ีซ
    -0.06
     Sidd
    -0.06
     disconnect
    -0.06
    高等
    -0.06
    沒有
    -0.06
    762
    -0.06
    째
    -0.06
     Heads
    -0.06
     deber
    -0.06
    POSITIVE LOGITS
    FFE
    0.08
    RES
    0.07
    ty
    0.07
    riba
    0.07
    DATE
    0.07
    �
    0.06
    (character
    0.06
     فرهنگ
    0.06
     YOUR
    0.06
    Japanese
    0.06
    Act Density 0.000%

    No Known Activations