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

    Neuronpedia

    INDEX
    Explanations

    future research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    勰
    0.51
     Marissa
    0.49
    urés
    0.47
    igi
    0.47
     Zoro
    0.47
    🏨
    0.47
     করিতেছিল
    0.47
    нику
    0.46
    ьи
    0.46
     infek
    0.46
    POSITIVE LOGITS
    fn
    0.54
    vertical
    0.54
    '
    0.52
    DEN
    0.50
    ↵
    0.49
    lat
    0.49
    southern
    0.48
    ft
    0.47
    \
    0.47
    green
    0.46
    Act Density 0.001%

    No Known Activations