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

    Neuronpedia

    INDEX
    Explanations

    large language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سلاٹس
    0.48
     Mackay
    0.43
    DEPENDENCIA
    0.42
    ња
    0.41
    駙
    0.40
    Jacobi
    0.39
     usuários
    0.39
     sürekli
    0.39
     кварти
    0.39
    鯽
    0.39
    POSITIVE LOGITS
    o
    0.43
     model
    0.42
    model
    0.42
    room
    0.41
    р
    0.40
    г
    0.40
    ർ
    0.40
    oms
    0.40
    -
    0.39
     again
    0.38
    Act Density 0.016%

    No Known Activations