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

    Neuronpedia

    INDEX
    Explanations

    Database, DB, library

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.52
    hla
    0.52
     can
    0.52
    ا
    0.51
    s
    0.50
    b
    0.49
    葉
    0.48
    caria
    0.48
    лів
    0.47
    اهر
    0.47
    POSITIVE LOGITS
    thickmathspace
    0.55
     সাঁ
    0.55
    EventQueue
    0.54
    ท่า
    0.54
     ⚫
    0.52
    ères
    0.52
     `'\\
    0.51
     unsh
    0.50
    㵴
    0.50
    ებისთვის
    0.49
    Act Density 0.000%

    No Known Activations