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

    Neuronpedia

    INDEX
    Explanations

    Exclusion prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     _(
    -0.06
    Ｄ
    -0.06
    ENSITY
    -0.06
     lur
    -0.06
    лара
    -0.06
     switching
    -0.06
    .analytics
    -0.06
     超
    -0.06
     Unable
    -0.06
    |.
    -0.06
    POSITIVE LOGITS
     naken
    0.07
    quake
    0.06
    .FromResult
    0.06
    oon
    0.06
     thirty
    0.06
     neckline
    0.06
     headaches
    0.06
     Orient
    0.06
     smelling
    0.06
    istle
    0.06
    Act Density 0.054%

    No Known Activations