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

    Neuronpedia

    INDEX
    Explanations

    {\

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Soc
    -0.07
     IQ
    -0.06
     её
    -0.06
     @}
    -0.06
     conditioning
    -0.06
     Roku
    -0.06
     Becker
    -0.06
     mee
    -0.06
     Debian
    -0.06
    911
    -0.06
    POSITIVE LOGITS
     filled
    0.07
    ография
    0.07
    (il
    0.07
    NE
    0.07
    /Observable
    0.07
    ,date
    0.06
    uccess
    0.06
    0.06
     kodu
    0.06
    caught
    0.06
    Act Density 0.003%

    No Known Activations