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

    Neuronpedia

    INDEX
    Explanations

    equals symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovich
    -0.07
     adamant
    -0.07
    grading
    -0.06
    Moon
    -0.06
     що
    -0.06
     주
    -0.06
     wartime
    -0.06
    ↵
↵
    -0.06
    裡
    -0.06
    icked
    -0.06
    POSITIVE LOGITS
    mez
    0.07
     sistemas
    0.07
    Genesis
    0.06
     Factory
    0.06
     veya
    0.06
     chảy
    0.06
    icaid
    0.06
    ึกษ
    0.06
     investigación
    0.06
     SME
    0.06
    Act Density 0.002%

    No Known Activations