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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ablanca
    -0.08
    Lor
    -0.08
     governor
    -0.08
    Gru
    -0.07
    orption
    -0.07
     firewall
    -0.07
    aso
    -0.07
     شهر
    -0.07
    _online
    -0.07
     अधिकारी
    -0.07
    POSITIVE LOGITS
     zacz
    0.09
    身体
    0.09
     pest
    0.09
     શરૂ
    0.09
     тән
    0.09
     introd
    0.09
     ladan
    0.08
    १८
    0.08
     ortaya
    0.08
    ১৮
    0.08
    Act Density 0.025%

    No Known Activations