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

    Neuronpedia

    INDEX
    Explanations

    Lists and tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ూ
    -0.08
     MC
    -0.08
    /or
    -0.07
     sing
    -0.07
     ощ
    -0.07
     university
    -0.07
     rocky
    -0.07
    ongodb
    -0.07
    나요
    -0.07
     متفاوت
    -0.07
    POSITIVE LOGITS
     Finally
    0.08
    0.08
     Slovenije
    0.08
    hour
    0.07
    mutable
    0.07
    زه
    0.07
    hum
    0.07
    ісля
    0.07
     chased
    0.07
     ஆகிய
    0.07
    Act Density 0.092%
    No Known Activations