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

    Neuronpedia

    INDEX
    Explanations

    tell me everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ট্যাব
    0.47
     স্বাভাবিক
    0.46
     코드
    0.46
     구
    0.44
     일본
    0.43
    presa
    0.43
     오히려
    0.42
    约为
    0.41
     일반
    0.40
     সম্মান
    0.40
    POSITIVE LOGITS
    "
    0.47
    m
    0.46
    ")
    0.45
    a
    0.44
    ",
    0.44
    "',
    0.43
    Q
    0.42
    Ф
    0.42
    Fprintf
    0.42
    H
    0.41
    Act Density 0.034%

    No Known Activations