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

    Neuronpedia

    INDEX
    Explanations

    historical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dépassant
    0.62
    办法
    0.56
    apanam
    0.51
     অপহরণকারীদের
    0.50
     calab
    0.47
     охла
    0.45
     automática
    0.45
    𝒖
    0.45
     zodat
    0.44
     interesa
    0.44
    POSITIVE LOGITS
     World
    0.50
     Discovery
    0.50
     History
    0.47
     Russia
    0.47
     f
    0.46
     Commission
    0.46
     Rel
    0.45
     American
    0.45
     Victory
    0.44
     Tolkien
    0.43
    Act Density 0.001%

    No Known Activations