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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     首
    -0.07
    áže
    -0.06
    afia
    -0.06
     contrato
    -0.06
    ovaly
    -0.06
     potent
    -0.06
     Tanrı
    -0.06
     Focus
    -0.06
    ';";↵
    -0.06
    .Created
    -0.06
    POSITIVE LOGITS
     arbit
    0.07
     ω
    0.06
    \admin
    0.06
    orum
    0.06
    REFERRED
    0.06
     significa
    0.06
     abdom
    0.06
     Purch
    0.06
    gings
    0.06
     Sco
    0.06
    Act Density 0.002%

    No Known Activations