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

    Neuronpedia

    INDEX
    Explanations

    various topics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Nella
    0.44
    Dopo
    0.42
     Để
    0.42
    Để
    0.41
    Pentru
    0.40
     Además
    0.40
    Após
    0.40
    Cuando
    0.39
     Pokud
    0.39
     Después
    0.39
    POSITIVE LOGITS
     ре
    0.33
     си
    0.31
     ф
    0.28
     framework
    0.28
     много
    0.27
     ин
    0.27
     концеп
    0.27
     ли
    0.26
     ша
    0.26
     три
    0.26
    Act Density 0.225%

    No Known Activations