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

    Neuronpedia

    INDEX
    Explanations

    metal, media, SOLID, fossil, nuclei

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )_{
    0.45
    ঙ্গা
    0.42
    (@"
    0.41
    ／
    0.39
    ocsát
    0.38
    ку
    0.38
    ινων
    0.38
     shortstop
    0.37
    吃到
    0.37
    ικού
    0.36
    POSITIVE LOGITS
    尤其是
    0.52
    類の
    0.52
     各
    0.50
     종류
    0.48
     jeweil
    0.45
    特别是
    0.44
     особенно
    0.44
     भाषाओं
    0.44
    類的
    0.42
     обоих
    0.42
    Act Density 0.912%

    No Known Activations