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

    Neuronpedia

    INDEX
    Explanations

    markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lda
    -0.07
    іту
    -0.06
     XL
    -0.06
    ğitim
    -0.06
     Cooperative
    -0.06
     continuously
    -0.06
     Sundays
    -0.06
    氣
    -0.06
    เ
    -0.06
    ATEG
    -0.06
    POSITIVE LOGITS
     marker
    0.11
     markers
    0.10
    arkers
    0.07
     bestselling
    0.07
    .tipo
    0.07
     crest
    0.07
    ires
    0.07
     beacon
    0.06
    Dry
    0.06
     Lamar
    0.06
    Act Density 0.005%

    No Known Activations