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

    Neuronpedia

    INDEX
    Explanations

    units per

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     служба
    0.39
     серви
    0.37
    馔
    0.37
    精华
    0.36
     प्रत्येक
    0.36
     тариф
    0.36
    रीबन
    0.35
    각
    0.34
    лишком
    0.34
     решение
    0.34
    POSITIVE LOGITS
    per
    0.42
    %,
    0.39
    b
    0.39
    n
    0.38
    -
    0.38
     per
    0.36
    m
    0.36
    k
    0.35
    p
    0.35
     units
    0.35
    Act Density 0.029%

    No Known Activations