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

    Neuronpedia

    INDEX
    Explanations

    artificial intelligence risks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ới
    -0.07
    InternalEnumerator
    -0.06
     invis
    -0.06
    811
    -0.06
    आ
    -0.06
    Meg
    -0.06
    ์อ
    -0.06
     konce
    -0.06
    xlabel
    -0.06
     consultant
    -0.06
    POSITIVE LOGITS
    .done
    0.07
     dioxide
    0.07
     experimenting
    0.06
     setContent
    0.06
     strikes
    0.06
     fucks
    0.06
     rejoice
    0.06
    ollect
    0.06
    EventData
    0.06
    askan
    0.06
    Act Density 0.046%

    No Known Activations