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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    व्यक्तित्व
    0.40
    权力
    0.40
     Và
    0.39
     солнце
    0.39
    谚
    0.38
     Colours
    0.38
    阳光
    0.36
    etrotters
    0.36
     marginalised
    0.36
    强势
    0.36
    POSITIVE LOGITS
    Reuse
    0.43
     nonzero
    0.39
    PhysRev
    0.38
    ਜ਼
    0.38
     nonlocal
    0.37
    ͓
    0.37
     importar
    0.36
     ${\
    0.35
    uminescence
    0.35
     طول
    0.34
    Act Density 0.001%

    No Known Activations