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

    Neuronpedia

    INDEX
    Explanations

    Code, URLs, documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    crud
    -0.30
    ipl
    -0.30
    rians
    -0.29
    irez
    -0.25
    ä¿¡
    -0.24
    tz
    -0.24
    .bel
    -0.24
     maintaining
    -0.24
     Ou
    -0.24
     maintained
    -0.24
    POSITIVE LOGITS
    éĢģåĩº
    0.35
    çĹ£
    0.27
    类似çļĦ
    0.26
     invert
    0.25
    éĢģåİ»
    0.25
    è¡Įãģ£ãģŁ
    0.24
     ass
    0.24
    PED
    0.24
     Lid
    0.24
    åIJĮçŃī
    0.23
    Act Density 0.017%

    No Known Activations