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

    Neuronpedia

    INDEX
    Explanations

    explaining a situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apasion
    0.49
     passionate
    0.44
     accessed
    0.44
     overarching
    0.44
     utilizing
    0.43
     costru
    0.42
     organized
    0.42
     utilized
    0.42
     شركات
    0.42
     conness
    0.41
    POSITIVE LOGITS
    Ф
    0.49
    eningen
    0.46
    <
    0.45
     Би
    0.45
    З
    0.45
    icias
    0.44
    Би
    0.44
    Во
    0.43
    为其
    0.43
    سلام
    0.43
    Act Density 0.013%

    No Known Activations