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

    Neuronpedia

    INDEX
    Explanations

    Health issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LayoutInflater
    -0.07
    (recipe
    -0.06
     이렇게
    -0.06
    hydro
    -0.06
    rel
    -0.06
    >.↵
    -0.06
    rift
    -0.06
     clients
    -0.06
    }:
    -0.06
    ].↵
    -0.06
    POSITIVE LOGITS
     pursue
    0.07
     incess
    0.07
     qual
    0.06
     conducive
    0.06
    inished
    0.06
     remed
    0.06
     počíta
    0.06
     Yönetim
    0.06
     Supplementary
    0.06
    Github
    0.06
    Act Density 0.069%

    No Known Activations