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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dealt
    -0.06
     inequality
    -0.06
    ва
    -0.06
     rand
    -0.06
     relied
    -0.06
     gratitude
    -0.06
    988
    -0.06
    .ForeColor
    -0.06
     shiny
    -0.06
     sent
    -0.06
    POSITIVE LOGITS
    (Database
    0.07
     Arbitrary
    0.07
    .series
    0.07
    ária
    0.06
    .pet
    0.06
    asco
    0.06
     Hebrew
    0.06
     Road
    0.06
     Imperial
    0.06
    The
    0.06
    Act Density 0.060%

    No Known Activations