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

    Neuronpedia

    INDEX
    Explanations

    indices in mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ज्ञानिक
    0.38
    摈
    0.38
    ंदरे
    0.38
    黢
    0.37
    赶紧
    0.37
    现代化
    0.37
    둰
    0.37
    珵
    0.37
    愊
    0.36
    䆔
    0.35
    POSITIVE LOGITS
    _{
    0.59
    ij
    0.50
    _{\
    0.49
    <sub>
    0.49
     i
    0.46
     j
    0.45
    _
    0.43
    }^{
    0.42
    }_{
    0.42
    j
    0.42
    Act Density 0.039%

    No Known Activations