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

    Neuronpedia

    INDEX
    Explanations

    affairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mỗi
    -0.07
    CustomLabel
    -0.06
     kitten
    -0.06
     Oxygen
    -0.06
    November
    -0.06
     dagen
    -0.06
     بتوان
    -0.06
    itizer
    -0.06
     onion
    -0.06
    mıyor
    -0.06
    POSITIVE LOGITS
     affairs
    0.11
     Affairs
    0.10
     affair
    0.09
     seria
    0.07
     referee
    0.07
     disciplinary
    0.07
    iff
    0.07
     defends
    0.07
    /cms
    0.07
     War
    0.07
    Act Density 0.005%

    No Known Activations