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

    Neuronpedia

    INDEX
    Explanations

    this followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сюда
    0.74
    Questa
    0.64
    вед
    0.64
     данном
    0.63
    ---
    0.63
     beneath
    0.62
     этим
    0.62
    स्स
    0.61
    --
    0.61
    PagerAdapter
    0.61
    POSITIVE LOGITS
     erfolgt
    0.84
     done
    0.77
     yapılır
    0.76
     takes
    0.76
     Then
    0.76
     means
    0.74
     Done
    0.72
     делается
    0.71
     then
    0.70
    Then
    0.70
    Act Density 0.214%

    No Known Activations