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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ecl
    -0.06
    stances
    -0.06
     Petro
    -0.06
     namedtuple
    -0.06
    +x
    -0.06
    .ACTION
    -0.06
    资
    -0.06
     dusk
    -0.06
    ijkstra
    -0.06
     idx
    -0.06
    POSITIVE LOGITS
    UTOR
    0.08
     migli
    0.07
     relinqu
    0.06
     culpa
    0.06
    isky
    0.06
    IELD
    0.06
    ピー
    0.06
    .jpeg
    0.06
    ={
    0.06
    ریز
    0.06
    Act Density 0.300%

    No Known Activations