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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.57
    5
    0.55
    .
    0.50
     The
    0.49
    ون
    0.47
    6
    0.47
    这个
    0.46
    ↵
    0.45
    0
    0.45
    4
    0.45
    POSITIVE LOGITS
    <unused2054>
    0.53
     stockfoto
    0.49
     fontos
    0.48
     skapa
    0.47
    <unused999>
    0.47
    只限平日
    0.47
     zeigt
    0.47
     koncept
    0.46
     byen
    0.46
     wodurch
    0.46
    Act Density 0.294%

    No Known Activations