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

    Neuronpedia

    INDEX
    Explanations

    emergency services:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     T
    0.50
    0.49
     Agreements
    0.48
     be
    0.47
     L
    0.46
     Times
    0.46
     Orders
    0.45
     all
    0.45
     Europe
    0.44
     za
    0.44
    POSITIVE LOGITS
    。
    0.52
    ։
    0.47
    Pergunta
    0.47
    疳
    0.46
    白い
    0.46
     енер
    0.46
    Energie
    0.46
    скет
    0.46
    ഃ
    0.46
    Brick
    0.45
    Act Density 0.012%

    No Known Activations