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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (AL
    -0.07
     ro
    -0.07
    間に
    -0.06
    (Icons
    -0.06
     drones
    -0.06
    .showError
    -0.06
     články
    -0.06
    Disallow
    -0.06
    ARB
    -0.06
    ncoder
    -0.06
    POSITIVE LOGITS
    签
    0.07
     фах
    0.07
     жид
    0.07
    ühl
    0.06
     nestled
    0.06
     aforementioned
    0.06
    ele
    0.06
    ып
    0.06
     timely
    0.06
     leer
    0.06
    Act Density 0.006%

    No Known Activations