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

    Neuronpedia

    INDEX
    Explanations

    said that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     male
    0.38
     এইভাবে
    0.38
    $-[
    0.38
     así
    0.37
    Aby
    0.37
    Male
    0.37
    आइ
    0.36
     thus
    0.36
     otor
    0.36
    By
    0.35
    POSITIVE LOGITS
    intah
    0.42
     cotidiana
    0.40
     कदम
    0.39
     городских
    0.39
    各位同學
    0.39
     जागरूक
    0.38
     ModelState
    0.38
    蒟
    0.38
     الطعام
    0.37
    essels
    0.37
    Act Density 0.000%

    No Known Activations