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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     succès
    -0.07
    Legend
    -0.07
     Rico
    -0.07
    ﾘ
    -0.07
     Vinci
    -0.06
     Walt
    -0.06
    Jim
    -0.06
    004
    -0.06
    Tur
    -0.06
    Cho
    -0.06
    POSITIVE LOGITS
    商
    0.06
     McA
    0.06
    ,port
    0.06
     chữ
    0.06
     axs
    0.06
    ,length
    0.06
    ίναι
    0.06
    .Fatal
    0.06
     skipping
    0.06
    _subs
    0.06
    Act Density 0.006%

    No Known Activations