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

    Neuronpedia

    INDEX
    Explanations

    novel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ▘
    -0.08
    (pol
    -0.07
     Over
    -0.07
    栉
    -0.07
    fäh
    -0.07
    moving
    -0.07
     wik
    -0.07
     IEEE
    -0.06
    -0.06
     обеспеч
    -0.06
    POSITIVE LOGITS
    \Context
    0.08
    _cash
    0.07
     tissue
    0.07
     Realty
    0.07
    disabled
    0.07
     searchBar
    0.07
    روح
    0.07
    .className
    0.07
    .pojo
    0.06
    rh
    0.06
    Act Density 0.052%

    No Known Activations