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

    Neuronpedia

    INDEX
    Explanations

    country

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Exhibition
    -0.07
    Processes
    -0.07
    Explorer
    -0.07
     лак
    -0.07
     Watches
    -0.07
    HSV
    -0.07
    Met
    -0.06
    _DETECT
    -0.06
    και
    -0.06
    Office
    -0.06
    POSITIVE LOGITS
     congr
    0.08
    طي
    0.06
    /v
    0.06
    (skip
    0.06
     GNUNET
    0.06
    ncias
    0.06
     manic
    0.06
     sugars
    0.06
    ülen
    0.06
    clear
    0.06
    Act Density 0.004%

    No Known Activations