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

    Neuronpedia

    INDEX
    Explanations

    task

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    speakers
    1.39
    ꜱ
    1.39
    sock
    1.30
    at
    1.29
    ᴛ
    1.26
     `<`,
    1.26
    上午
    1.22
     şekilde
    1.22
     mulighed
    1.17
    יים
    1.17
    POSITIVE LOGITS
    ک
    1.27
    ك
    1.13
    ни
    1.08
    о
    1.03
    bbene
    1.02
    ش
    1.02
    오늘
    1.02
     task
    1.00
     seva
    1.00
     tasks
    0.98
    Act Density 0.495%

    No Known Activations