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

    Neuronpedia

    INDEX
    Explanations

    World Bank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    authorization
    -0.70
    Dao
    -0.69
    Electric
    -0.68
    лё
    -0.66
    rickson
    -0.66
    šte
    -0.66
    たとえば
    -0.66
    手を
    -0.66
    ادة
    -0.65
    异步
    -0.65
    POSITIVE LOGITS
     majestic
    0.84
    ෛ
    0.82
     cette
    0.80
     leitor
    0.80
    匿名使用者
    0.77
     molto
    0.76
     промы
    0.75
    continence
    0.73
     cujo
    0.73
     drains
    0.73
    Act Density 0.031%

    No Known Activations