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

    Neuronpedia

    INDEX
    Explanations

    this [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ud
    0.33
    จะ
    0.33
    í
    0.33
    បញ្ចប់
    0.32
    <unused1043>
    0.32
    <unused1122>
    0.31
    ைகள்
    0.30
    是
    0.30
    鎊
    0.30
    <unused552>
    0.30
    POSITIVE LOGITS
    i
    0.39
    r
    0.36
    '
    0.34
    ין
    0.33
    today
    0.31
     چنین
    0.30
     स्थिती
    0.29
    ान
    0.29
     this
    0.29
    ipe
    0.28
    Act Density 0.115%

    No Known Activations