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

    Neuronpedia

    INDEX
    Explanations

    prediction set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ગૃહ
    0.45
     المنزل
    0.44
    建
    0.38
     số
    0.38
    本セット
    0.38
    emplo
    0.38
    イト
    0.37
     本体
    0.37
    totalPages
    0.37
    ុល
    0.37
    POSITIVE LOGITS
     cui
    0.50
     undead
    0.45
     cartoon
    0.44
    🤪
    0.44
     suave
    0.43
    дора
    0.43
     supernatural
    0.43
     Lobby
    0.42
     Webin
    0.42
     YouTube
    0.42
    Act Density 0.005%

    No Known Activations