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

    Neuronpedia

    INDEX
    Explanations

    contentEditable or content scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    production
    0.45
     creation
    0.43
     creazione
    0.43
     creación
    0.43
    作成
    0.43
     제작
    0.43
    creation
    0.41
     producción
    0.39
     ایجاد
    0.38
    шат
    0.38
    POSITIVE LOGITS
     lan
    0.39
    ceed
    0.38
     bie
    0.38
    ാ
    0.38
    ंच
    0.37
    Modelo
    0.37
    ρού
    0.37
     Ender
    0.37
    溫
    0.37
     sparen
    0.37
    Act Density 0.006%

    No Known Activations