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

    Neuronpedia

    INDEX
    Explanations

    message

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     REVIEW
    -0.07
     seventeen
    -0.06
    Named
    -0.06
     numpy
    -0.06
     controversy
    -0.06
    inge
    -0.06
     chopping
    -0.06
    嘉
    -0.06
    ‌خ
    -0.06
     lunch
    -0.06
    POSITIVE LOGITS
     message
    0.07
     Bran
    0.07
    Mensaje
    0.07
    -bodied
    0.06
     Böyle
    0.06
     Gathering
    0.06
     trước
    0.06
     Nasıl
    0.06
     गए
    0.06
     ApplicationUser
    0.06
    Act Density 0.023%

    No Known Activations