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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upbeat
    -0.07
     vista
    -0.07
    _Write
    -0.06
     нее
    -0.06
     depreci
    -0.06
    .pair
    -0.06
     dado
    -0.06
    Louis
    -0.06
    lined
    -0.06
    vip
    -0.06
    POSITIVE LOGITS
     PMC
    0.07
     priv
    0.06
    __:
    0.06
     RGB
    0.06
     Orwell
    0.06
     verdienen
    0.06
     disag
    0.06
     legitimate
    0.06
    geometry
    0.06
     underwater
    0.06
    Act Density 0.077%

    No Known Activations