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

    Neuronpedia

    INDEX
    Explanations

    North Carolina facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    1.14
    ，
    1.12
    .
    0.93
     tenements
    0.90
    (
    0.84
    -
    0.79
     nations
    0.76
    Ships
    0.75
     hostels
    0.74
     думать
    0.74
    POSITIVE LOGITS
    ри
    1.16
    ى
    1.16
    p
    1.02
    b
    1.00
    рай
    0.98
    us
    0.96
    ak
    0.96
    al
    0.96
    িবার
    0.95
    에
    0.95
    Act Density 0.001%

    No Known Activations