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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Parks
    -0.07
     صالح
    -0.06
    .WebElement
    -0.06
    	right
    -0.06
    .buttons
    -0.06
    plates
    -0.06
     conc
    -0.06
    Pay
    -0.06
    increments
    -0.06
    ывая
    -0.06
    POSITIVE LOGITS
    tensor
    0.07
    Safety
    0.06
    kového
    0.06
    .ct
    0.06
     Ik
    0.06
    nod
    0.06
     continuity
    0.06
    luluk
    0.06
     )}↵
    0.06
    _distribution
    0.06
    Act Density 0.091%

    No Known Activations