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

    Neuronpedia

    INDEX
    Explanations

    Rules/Regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clk
    -0.07
     {/*
    -0.06
    semester
    -0.06
     SUMMARY
    -0.06
    .=
    -0.06
    13
    -0.06
    {/*
    -0.06
    šetř
    -0.06
    trainer
    -0.06
    }}}
    -0.06
    POSITIVE LOGITS
    jed
    0.06
    .home
    0.06
     Ads
    0.06
     appeal
    0.06
     WTF
    0.06
    bí
    0.06
    евой
    0.06
     meş
    0.06
     Uni
    0.05
    .sort
    0.05
    Act Density 0.021%

    No Known Activations