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

    Neuronpedia

    INDEX
    Explanations

    raid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GU
    -0.07
    .ConnectionStrings
    -0.07
    命令
    -0.07
    ені
    -0.06
    468
    -0.06
     FAR
    -0.06
     객
    -0.06
    ateway
    -0.06
     mus
    -0.06
    　　　　　　　　
    -0.06
    POSITIVE LOGITS
     declares
    0.07
     unethical
    0.06
     Saunders
    0.06
     Fraction
    0.06
     Liberties
    0.06
     influences
    0.06
     teammates
    0.06
    едак
    0.06
     вий
    0.06
     excerpt
    0.06
    Act Density 0.009%

    No Known Activations