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

    Neuronpedia

    INDEX
    Explanations

    math and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     밝
    -0.07
    .ac
    -0.07
     bin
    -0.07
    CEE
    -0.07
     Flux
    -0.07
     consultations
    -0.07
    _track
    -0.06
     behaviours
    -0.06
     Employer
    -0.06
     Hercules
    -0.06
    POSITIVE LOGITS
    จะต
    0.06
    。“
    0.06
    シャル
    0.06
     wore
    0.06
    cookie
    0.06
    аж
    0.06
    死亡
    0.06
    (rowIndex
    0.06
    Tom
    0.06
    =device
    0.05
    Act Density 0.129%

    No Known Activations