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

    Neuronpedia

    INDEX
    Explanations

    Polarized light

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /xml
    -0.07
     greenhouse
    -0.07
    켙
    -0.07
    ᱚ
    -0.07
    DatePicker
    -0.07
    Cap
    -0.07
    院长
    -0.07
    减持
    -0.07
     intellectual
    -0.07
     throughout
    -0.07
    POSITIVE LOGITS
    _rule
    0.07
    şek
    0.07
     podem
    0.07
    elper
    0.07
     Rew
    0.07
    静态
    0.07
    inge
    0.06
     jours
    0.06
    olding
    0.06
    つき
    0.06
    Act Density 0.008%

    No Known Activations