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

    Neuronpedia

    INDEX
    Explanations

    existence and validity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    specific
    -0.07
     televizyon
    -0.07
    忙
    -0.06
     항
    -0.06
    =\"#
    -0.06
     stuffed
    -0.06
     уг
    -0.06
    (tag
    -0.06
    ()<<"
    -0.06
    (D
    -0.06
    POSITIVE LOGITS
    เผ
    0.06
     initialValues
    0.06
     dashes
    0.06
    •↵↵
    0.06
    Readable
    0.06
     Subcommittee
    0.06
     Doğ
    0.06
    utoff
    0.06
     bietet
    0.06
    Drivers
    0.06
    Act Density 0.103%

    No Known Activations