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

    Neuronpedia

    INDEX
    Explanations

    bit manipulation and linear algebra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     включает
    0.56
     शामिल
    0.52
     bunların
    0.51
     मापने
    0.50
     incluyen
    0.50
    狞
    0.50
     inclui
    0.50
     incluye
    0.49
     bağlı
    0.48
     medición
    0.47
    POSITIVE LOGITS
    i
    0.50
    ly
    0.46
    on
    0.44
    D
    0.44
    ce
    0.43
    ities
    0.43
    best
    0.42
    en
    0.41
    ph
    0.41
    formed
    0.40
    Act Density 0.010%

    No Known Activations