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

    Neuronpedia

    INDEX
    Explanations

    json structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িয়েত
    0.42
    <unused1112>
    0.41
    ουλ
    0.40
    MessageNow
    0.38
    িবেন
    0.38
    رو
    0.37
    گران
    0.37
    velyan
    0.37
    xSpeed
    0.37
    ೇವಿನ
    0.37
    POSITIVE LOGITS
     {
    0.59
     که
    0.40
     yılında
    0.39
     The
    0.39
     ${
    0.39
     और
    0.38
     которая
    0.38
     [
    0.38
     {{
    0.38
     کے
    0.38
    Act Density 0.018%

    No Known Activations