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

    Neuronpedia

    INDEX
    Explanations

    language specification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Posts
    -0.06
    โต
    -0.06
     proport
    -0.06
     ders
    -0.06
     pope
    -0.06
     bred
    -0.06
    #a
    -0.06
     khoản
    -0.06
     pobl
    -0.06
    datatable
    -0.06
    POSITIVE LOGITS
     můž
    0.06
    .ordinal
    0.06
    .ai
    0.06
    ibrary
    0.06
    ocale
    0.06
     зелен
    0.06
    ("__
    0.06
    linky
    0.06
    ":↵
    0.06
    oration
    0.06
    Act Density 0.009%

    No Known Activations