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

    Neuronpedia

    INDEX
    Explanations

    must

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _report
    -0.07
     duż
    -0.07
     cavity
    -0.06
    inant
    -0.06
    Major
    -0.06
     ifndef
    -0.06
    outdir
    -0.06
    —even
    -0.06
     soda
    -0.06
    绝
    -0.06
    POSITIVE LOGITS
    rede
    0.07
    DETAIL
    0.06
     Hed
    0.06
     electoral
    0.06
    leshooting
    0.06
    232
    0.06
    بح
    0.06
     leaderboard
    0.06
    篇
    0.06
    unge
    0.05
    Act Density 0.051%

    No Known Activations