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

    Neuronpedia

    INDEX
    Explanations

    red

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused597>
    0.53
    <unused2171>
    0.53
    <unused2121>
    0.51
     நிர்வாக
    0.50
    <unused2118>
    0.49
    <unused2206>
    0.49
    <unused2178>
    0.49
     سه
    0.48
    <unused1712>
    0.48
    <unused2137>
    0.48
    POSITIVE LOGITS
    स्सी
    0.51
    astaan
    0.50
     Position
    0.49
     बेकार
    0.49
    Movie
    0.49
    acariy
    0.49
    ोज़
    0.48
     Football
    0.48
    Position
    0.47
    movie
    0.47
    Act Density 0.494%

    No Known Activations