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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UIT
    -0.08
    _net
    -0.07
    (Qt
    -0.07
     Boot
    -0.07
    IT
    -0.07
     Hot
    -0.07
     Ont
    -0.06
     idiot
    -0.06
    -domain
    -0.06
     Capability
    -0.06
    POSITIVE LOGITS
     closer
    0.08
    .Align
    0.08
     more
    0.08
     anymore
    0.07
     hasNext
    0.07
     Corrections
    0.07
    体育
    0.06
     ГО
    0.06
     같
    0.06
    mile
    0.06
    Act Density 0.011%

    No Known Activations