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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PopupMenu
    -0.07
     Mediterranean
    -0.07
     navigationController
    -0.07
     enormous
    -0.07
     cause
    -0.07
     polynomial
    -0.07
     الثالث
    -0.07
    bere
    -0.06
     дослідження
    -0.06
    亮
    -0.06
    POSITIVE LOGITS
     civilian
    0.07
    privacy
    0.07
     never
    0.06
     러
    0.06
     Stories
    0.06
     JT
    0.06
     Medal
    0.06
    ckeditor
    0.06
    serial
    0.05
    nothing
    0.05
    Act Density 0.003%

    No Known Activations