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

    Neuronpedia

    INDEX
    Explanations

    developing, resolve, fires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     взаимодействие
    0.50
     assistir
    0.48
     Grenzen
    0.45
     apaixon
    0.45
     constater
    0.45
     quienes
    0.45
     avanç
    0.45
     regarder
    0.43
     savent
    0.43
     humiliation
    0.42
    POSITIVE LOGITS
    ครบ
    0.45
    需要的
    0.43
     crumbs
    0.41
    /
    0.40
    準備
    0.40
    实例
    0.40
    或
    0.40
    ORT
    0.39
     be
    0.39
     route
    0.39
    Act Density 0.018%

    No Known Activations